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

    Neuronpedia

    INDEX
    Explanations

    741741 crisis helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    র
    0.54
    los
    0.54
     immagine
    0.51
     exatamente
    0.50
    nikiem
    0.49
     mastect
    0.47
    rza
    0.47
    ল
    0.46
    nél
    0.46
     画像
    0.46
    POSITIVE LOGITS
     DAYS
    0.54
     days
    0.52
    ك
    0.48
    ಾವ
    0.48
    до
    0.46
     giorni
    0.44
    days
    0.43
     días
    0.43
    ود
    0.41
    သင့်
    0.41
    Act Density 0.031%

    No Known Activations