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

    Neuronpedia

    INDEX
    Explanations

    references to resolution-related concepts and entities

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

    Werner Heisenberg, Borel plane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ang
    -0.49
    катери
    -0.49
     Epif
    -0.46
    English
    -0.46
    ================
    -0.45
    Ang
    -0.45
    Ped
    -0.45
    Secondly
    -0.45
    Eu
    -0.43
    ╔
    -0.43
    POSITIVE LOGITS
    Resolver
    1.54
     Resolver
    1.51
    resolver
    1.45
     resolver
    1.27
     resol
    0.92
     resolving
    0.90
    resolvers
    0.89
     resolution
    0.86
     Resolution
    0.85
     resolves
    0.84
    Act Density 0.001%

    No Known Activations