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

    Neuronpedia

    INDEX
    Explanations

    those with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Retrieve
    0.71
     遅く
    0.70
     retribution
    0.68
     Assign
    0.67
     وجہ
    0.67
     precludes
    0.67
     Administration
    0.66
     Administrative
    0.66
     Committees
    0.66
    ্বাস
    0.66
    POSITIVE LOGITS
    res
    0.92
    });
    0.83
    ية
    0.77
     jogo
    0.76
    s
    0.72
    amino
    0.71
    sn
    0.71
    姜
    0.70
    os
    0.70
    sa
    0.69
    Act Density 0.000%

    No Known Activations