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

    Neuronpedia

    INDEX
    Explanations

    crisis hotline contacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ゴム
    0.76
    جاد
    0.72
    ВД
    0.71
    ంద
    0.71
     곳
    0.71
    ioane
    0.69
     всеки
    0.69
     ৪০
    0.68
     Nove
    0.67
     সদ
    0.67
    POSITIVE LOGITS
     கற்ப
    0.73
     limiti
    0.66
    hou
    0.66
     limits
    0.66
     रोडवेज
    0.65
    concent
    0.65
     starved
    0.65
     marijuana
    0.64
     densité
    0.64
     capacit
    0.63
    Act Density 0.003%

    No Known Activations