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

    Neuronpedia

    INDEX
    Explanations

    references to "all"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.85
     ModelExpression
    -0.82
    دانشنامهٔ
    -0.78
    MessageOf
    -0.74
     ProtoMessage
    -0.74
    fromnode
    -0.73
    GOTREF
    -0.71
     financière
    -0.71
    protoimpl
    -0.71
    ValueStyle
    -0.69
    POSITIVE LOGITS
    -
    0.47
     new
    0.45
     all
    0.44
     happened
    0.43
    new
    0.43
     Lic
    0.42
     too
    0.40
    di
    0.40
     versus
    0.40
    orn
    0.39
    Act Density 0.003%

    No Known Activations