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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

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

    mathematical formulas and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.69
    ">//
    -0.69
     protoimpl
    -0.69
     Shakspeare
    -0.63
    +#+#
    -0.60
     myſelf
    -0.56
    Filmographie
    -0.56
     Cæsar
    -0.56
    BrowserModule
    -0.56
    -0.55
    POSITIVE LOGITS
    orElse
    0.35
    thenReturn
    0.32
    OrEqualTo
    0.32
     właśnie
    0.31
    ließlich
    0.29
     rather
    0.29
    TagMode
    0.28
     strane
    0.27
    ękuję
    0.27
     indeed
    0.27
    Act Density 0.374%

    No Known Activations