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

    Neuronpedia

    INDEX
    Explanations

    specific time or stage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Time
    0.38
    ersch
    0.36
    H
    0.35
    ಂಡ
    0.35
    Blood
    0.34
    এর
    0.34
    0.34
    Home
    0.33
     সংঘর্ষ
    0.33
    উ
    0.33
    POSITIVE LOGITS
     juncture
    0.53
    abouts
    0.52
    에서의
    0.48
     estágio
    0.44
     anyway
    0.42
     onwards
    0.41
     tabel
    0.40
    ของการ
    0.40
     circonstances
    0.40
     tabela
    0.39
    Act Density 0.014%

    No Known Activations