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

    Neuronpedia

    INDEX
    Explanations

    Targeting, Wait, provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    V
    0.88
     عب
    0.80
    G
    0.78
    ется
    0.77
    WAT
    0.77
    W
    0.76
    ный
    0.75
    Madame
    0.74
    ENGE
    0.73
    nolds
    0.73
    POSITIVE LOGITS
     sơ
    0.84
     Ingl
    0.75
     Inspire
    0.71
     incrementar
    0.70
     Forever
    0.70
     Alphabet
    0.70
     Desire
    0.70
     Octopus
    0.69
     xinh
    0.68
     Kuna
    0.68
    Act Density 0.002%

    No Known Activations