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

    Neuronpedia

    INDEX
    Explanations

    pretend to be / it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حداقل
    0.57
    ATORS
    0.55
     jedynie
    0.55
    少なくとも
    0.55
    bitos
    0.54
    uttosto
    0.52
     heathen
    0.52
    믄
    0.52
    کہ
    0.51
     Фурга
    0.51
    POSITIVE LOGITS
    ствие
    0.43
    พัก
    0.41
    服
    0.41
     change
    0.41
    Count
    0.39
     is
    0.39
     меня
    0.39
     sess
    0.39
    Change
    0.37
    ess
    0.37
    Act Density 0.000%

    No Known Activations