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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by related nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.91
    ه
    0.86
    ل
    0.80
    га
    0.79
    ج
    0.78
     in
    0.76
    ли
    0.76
    在
    0.76
    ن
    0.74
    can
    0.73
    POSITIVE LOGITS
    0.86
    ンの
    0.68
     is
    0.66
     on
    0.65
     Chihuahua
    0.64
     of
    0.63
     Soldaten
    0.62
     Steelers
    0.61
     UnwrapRef
    0.60
     Venezuelan
    0.60
    Act Density 0.111%

    No Known Activations