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

    Neuronpedia

    INDEX
    Explanations

    code snippet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坏事
    -0.07
    _checksum
    -0.07
    性命
    -0.06
    أشخاص
    -0.06
    /extensions
    -0.06
     Knee
    -0.06
    chas
    -0.06
    ähr
    -0.06
     יודעים
    -0.06
     Eigen
    -0.06
    POSITIVE LOGITS
    מדי
    0.08
    ับ
    0.07
     prints
    0.07
    醵
    0.07
    dbg
    0.07
     Reserve
    0.07
    叻
    0.07
    诒
    0.07
     automáticamente
    0.07
     Measures
    0.07
    Act Density 0.028%

    No Known Activations