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

    Neuronpedia

    INDEX
    Explanations

    governing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'id
    -0.07
    ˮ
    -0.07
    /documentation
    -0.07
    رؤية
    -0.06
    喧
    -0.06
     awe
    -0.06
     reluctant
    -0.06
     wary
    -0.06
    不足以
    -0.06
    _RANDOM
    -0.06
    POSITIVE LOGITS
    Leg
    0.07
    σ
    0.07
     blk
    0.07
    $self
    0.07
    тек
    0.07
     Ends
    0.07
     testers
    0.07
    bam
    0.07
     phúc
    0.07
     fold
    0.07
    Act Density 0.000%

    No Known Activations