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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     đều
    0.61
    ходили
    0.59
    都
    0.55
    都有
    0.54
     themselves
    0.54
     iban
    0.50
     pouvaient
    0.50
    Has
    0.47
    都很
    0.47
     بودند
    0.47
    POSITIVE LOGITS
     am
    1.41
     myself
    1.08
     हूं
    0.97
     हूँ
    0.95
     jestem
    0.91
    хожу
    0.88
     mijn
    0.82
     છું
    0.80
     моя
    0.77
     meine
    0.76
    Act Density 0.402%

    No Known Activations