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

    Neuronpedia

    INDEX
    Explanations

    build structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     explain
    0.63
    解釋
    0.58
    𝘾
    0.56
    西兰
    0.55
     Kotor
    0.55
    ณ
    0.55
    萤
    0.54
    ༠
    0.54
    颍
    0.54
    Cov
    0.53
    POSITIVE LOGITS
     amplifiers
    0.56
     prioridad
    0.55
     анато
    0.53
     ಪೂರ್ವ
    0.52
    clamp
    0.52
     Reliable
    0.52
     prefixed
    0.52
     audits
    0.51
     खुफिया
    0.51
     المتوسط
    0.50
    Act Density 0.000%

    No Known Activations