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

    Neuronpedia

    INDEX
    Explanations

    modules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    류
    -0.08
    单一
    -0.07
    wk
    -0.07
    펩
    -0.07
    isValid
    -0.07
     IGNORE
    -0.07
    FOUNDATION
    -0.07
    成人
    -0.07
     nhỏ
    -0.06
     Comprehensive
    -0.06
    POSITIVE LOGITS
     soir
    0.07
     Sundays
    0.06
     lou
    0.06
    我要
    0.06
    ;",
    0.06
    不得转载
    0.06
     Mia
    0.06
    𝐯
    0.06
    าร
    0.06
     euros
    0.06
    Act Density 0.001%

    No Known Activations