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

    Neuronpedia

    INDEX
    Explanations

    slavery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sincerity
    -0.08
    とのこと
    -0.07
     cabinets
    -0.07
    锅炉
    -0.06
     sacrificed
    -0.06
    麥
    -0.06
     zal
    -0.06
    ϕ
    -0.06
     amph
    -0.06
    车内
    -0.06
    POSITIVE LOGITS
    WebpackPlugin
    0.07
     wore
    0.07
    뿜
    0.07
    .coroutines
    0.06
    בסוף
    0.06
    ое
    0.06
    -groups
    0.06
    aravel
    0.06
    �
    0.06
     Eig
    0.06
    Act Density 0.026%

    No Known Activations