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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irc
    -0.08
    argo
    -0.07
    zem
    -0.07
    enable
    -0.07
    disable
    -0.07
     Kia
    -0.07
     DeV
    -0.07
    DATA
    -0.07
    acs
    -0.06
    MY
    -0.06
    POSITIVE LOGITS
     оконч
    0.06
    _added
    0.06
    清楚
    0.06
    _HOR
    0.06
    Namespace
    0.06
    leyin
    0.06
    ังส
    0.06
    appeared
    0.06
     LIST
    0.05
    Sphere
    0.05
    Act Density 0.009%

    No Known Activations