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

    Neuronpedia

    INDEX
    Explanations

    proper noun and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.18
     初始化
    1.18
     andRow
    1.17
     调用
    1.12
     获取
    1.12
    1.09
     ಮತ್ತು
    1.09
     返回
    1.09
    𒈨
    1.08
     және
    1.08
    POSITIVE LOGITS
    rog
    0.55
     ab
    0.41
     “
    0.40
    ens
    0.40
     ch
    0.39
    standing
    0.38
    H
    0.38
    im
    0.38
    G
    0.38
    S
    0.38
    Act Density 0.181%

    No Known Activations