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

    Neuronpedia

    INDEX
    Explanations

    SAMHSA National Helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deflected
    0.67
    让自己
    0.65
     sends
    0.65
     dejan
    0.63
     Suicide
    0.63
     hãy
    0.61
     ব্যাপারটা
    0.59
     sami
    0.58
     초
    0.57
     laissez
    0.57
    POSITIVE LOGITS
    于
    0.84
    itionally
    0.77
    pués
    0.76
    neath
    0.76
    vore
    0.75
    ැන
    0.74
    於
    0.71
    duğ
    0.71
    々の
    0.71
    ursa
    0.69
    Act Density 0.275%

    No Known Activations