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

    Neuronpedia

    INDEX
    Explanations

    conversation snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Eğ
    -0.07
    腿部
    -0.07
    方方面面
    -0.07
    bell
    -0.07
    毳
    -0.07
    _GF
    -0.07
     Pied
    -0.06
     før
    -0.06
     Ski
    -0.06
    POSITIVE LOGITS
    的看法
    0.08
    ':
↵
    0.07
    otation
    0.07
     execut
    0.07
    -address
    0.07
    力还是自
    0.07
    .compress
    0.07
    망
    0.07
    涡
    0.06
     breat
    0.06
    Act Density 0.162%

    No Known Activations