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

    Neuronpedia

    INDEX
    Explanations

    Habits, raising, using, arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    na
    0.50
    ty
    0.47
    met
    0.47
    tele
    0.46
    LA
    0.45
    s
    0.44
    SA
    0.44
    statt
    0.44
    SAR
    0.44
    ming
    0.43
    POSITIVE LOGITS
     İlç
    0.50
     ގ
    0.50
     மத
    0.49
    ěné
    0.49
     její
    0.49
     ඔබේ
    0.48
     İlçesi
    0.46
     acaba
    0.45
     videoj
    0.45
     ойной
    0.45
    Act Density 0.000%

    No Known Activations