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

    Neuronpedia

    INDEX
    Explanations

    basic actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zcela
    0.57
     tidak
    0.57
     ebenso
    0.56
    並不
    0.54
     nicht
    0.52
     reaping
    0.51
    并不
    0.50
     bukan
    0.50
    就不
    0.49
    比べて
    0.48
    POSITIVE LOGITS
    Ꮡ
    0.61
    Storia
    0.59
    0.58
     ﺍ
    0.57
    basic
    0.55
    ingh
    0.55
    asat
    0.55
    ll
    0.55
    impero
    0.55
     സമര
    0.54
    Act Density 0.000%

    No Known Activations