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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Preference
    -0.07
    土豆
    -0.07
    lüğü
    -0.07
    ircon
    -0.07
    (rank
    -0.06
    actory
    -0.06
    房间
    -0.06
     تن
    -0.06
    igan
    -0.06
    _lvl
    -0.06
    POSITIVE LOGITS
    THREAD
    0.08
     HE
    0.07
     Yes
    0.07
     UAE
    0.07
    メール
    0.07
    沉重
    0.07
    pthread
    0.07
    NB
    0.06
     Marxist
    0.06
     Forms
    0.06
    Act Density 0.008%

    No Known Activations