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

    Neuronpedia

    INDEX
    Explanations

    Legal documents/judgements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elasticity
    -0.07
    戴
    -0.07
    +-
    -0.07
    VERAGE
    -0.07
    Rel
    -0.07
    фор
    -0.07
     pole
    -0.07
    Stride
    -0.06
    =========
    -0.06
     Rel
    -0.06
    POSITIVE LOGITS
    "]))
    0.07
     ř
    0.06
     člověk
    0.06
    MethodBeat
    0.06
     undoubtedly
    0.06
    лось
    0.06
    $arity
    0.06
    .nil
    0.06
     attrib
    0.06
     obsess
    0.06
    Act Density 0.003%

    No Known Activations