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

    Neuronpedia

    INDEX
    Explanations

    disclaimers of professional advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.64
    ेशन
    0.59
    ूर
    0.58
    장
    0.58
    樂
    0.54
    Valor
    0.53
    เพิ่มเติม
    0.52
    Um
    0.51
    ou
    0.50
     leverage
    0.50
    POSITIVE LOGITS
    laki
    0.61
     جگہ
    0.60
    ്
    0.59
    л
    0.59
     MiG
    0.59
    ς
    0.59
    istan
    0.58
    actoring
    0.58
    आती
    0.58
    indices
    0.55
    Act Density 0.005%

    No Known Activations