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

    Neuronpedia

    INDEX
    Explanations

    names of characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    your
    0.96
     =>
    0.85
    Your
    0.84
    :
    0.80
     your
    0.80
     vaš
    0.79
     >=
    0.79
    你的
    0.77
     *
    0.77
     ஆகும்
    0.76
    POSITIVE LOGITS
     onlookers
    0.93
    两人
    0.89
     bewildered
    0.85
     startled
    0.84
     astonished
    0.81
     Clifford
    0.80
    兩人
    0.80
     Christians
    0.77
     exiled
    0.76
    bindingFields
    0.76
    Act Density 0.037%

    No Known Activations