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

    Neuronpedia

    INDEX
    Explanations

    7 days duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ンプ
    0.49
     Eller
    0.42
    нков
    0.41
    зова
    0.40
     sporadically
    0.40
     longitudine
    0.40
    ulan
    0.39
    ustering
    0.39
    odyne
    0.38
    हुआ
    0.38
    POSITIVE LOGITS
    CreateParams
    0.38
     Country
    0.36
     QUAL
    0.36
    prefs
    0.35
     Day
    0.35
     독
    0.34
     type
    0.34
    不想
    0.34
     dictatorship
    0.34
    븐
    0.34
    Act Density 0.000%

    No Known Activations