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

    Neuronpedia

    INDEX
    Explanations

    under/below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IB
    1.86
    ES
    1.69
    Oke
    1.66
    ным
    1.66
    Iddict
    1.65
    i
    1.62
    arati
    1.55
    an
    1.54
    ни
    1.52
    OB
    1.52
    POSITIVE LOGITS
     dạng
    1.86
    neath
    1.84
    下的
    1.77
    বিড়
    1.77
     koniec
    1.76
    ors
    1.72
    cence
    1.71
    د
    1.69
    ആര്‍
    1.68
     Conception
    1.64
    Act Density 0.292%

    No Known Activations