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

    Neuronpedia

    INDEX
    Explanations

    index of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的态度
    0.50
     Regional
    0.46
     क्षेत्रीय
    0.46
     PROJECT
    0.45
    ForRule
    0.42
    统治
    0.42
     અધિકારી
    0.41
    FBSDKInternal
    0.41
     Umgang
    0.41
    学家
    0.40
    POSITIVE LOGITS
     scars
    0.48
     outros
    0.48
     profits
    0.48
    other
    0.47
     surprises
    0.47
    new
    0.47
     shocks
    0.46
    zap
    0.46
     zooms
    0.46
    October
    0.45
    Act Density 0.000%

    No Known Activations