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

    Neuronpedia

    INDEX
    Explanations

    words indicating opinions or evaluations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    URBANA
    -0.46
     Donnerstag
    -0.44
    inine
    -0.44
    rog
    -0.43
    zzar
    -0.43
     she
    -0.42
    वा
    -0.42
    matig
    -0.41
    好吗
    -0.41
    ómetros
    -0.41
    POSITIVE LOGITS
     nhung
    0.63
    yntaxException
    0.63
    ="@+
    0.63
    Tetapi
    0.60
     nhưng
    0.59
    LEncoder
    0.57
    actionMode
    0.57
    IsMutable
    0.56
    googleapis
    0.56
     kaarangay
    0.55
    Act Density 0.660%

    No Known Activations