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

    Neuronpedia

    INDEX
    Explanations

    anything promising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ྪ
    0.91
     gême
    0.88
     personales
    0.86
     sacrament
    0.86
     ทีม
    0.85
     mesenteric
    0.82
     adsor
    0.82
    ியின்
    0.81
     liturgy
    0.81
     avances
    0.81
    POSITIVE LOGITS
    i
    1.02
    е
    0.96
    А
    0.90
    ه
    0.77
    นี่
    0.73
    t
    0.71
    т
    0.71
    or
    0.69
    ت
    0.69
    а
    0.68
    Act Density 0.003%

    No Known Activations