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

    Neuronpedia

    INDEX
    Explanations

    travel log and advisories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    1.75
    ات
    1.69
    sı
    1.65
    s
    1.58
    ف
    1.51
    ע
    1.45
    ру
    1.43
    ς
    1.41
     connues
    1.33
     waning
    1.32
    POSITIVE LOGITS
     marít
    1.71
    ys
    1.69
     inicio
    1.63
    mente
    1.61
    andolo
    1.60
    ist
    1.59
     naranja
    1.59
     óptica
    1.59
     compartido
    1.57
    ﺎ
    1.55
    Act Density 0.244%

    No Known Activations