Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Letters after arithmetic operations/variables

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligand
    -0.90
     league
    -0.89
     lieutenant
    -0.89
    Laboratory
    -0.87
     Laboratory
    -0.86
    Leadership
    -0.86
     leadership
    -0.85
     leagues
    -0.84
     liderazgo
    -0.83
     League
    -0.83
    POSITIVE LOGITS
    AccessorTable
    0.50
    таратура
    0.49
    omitempty
    0.45
    riwal
    0.45
     '\\;'
    0.43
     referrerpolicy
    0.40
    DIPSETTING
    0.39
    PhysRevD
    0.39
    CompilerServices
    0.38
    Portail
    0.37
    Act Density 0.363%

    No Known Activations