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

    Neuronpedia

    INDEX
    Explanations

    che

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نوشته
    -0.07
    ییر
    -0.07
     Nodes
    -0.07
     Wilson
    -0.06
    MBED
    -0.06
     struggled
    -0.06
    _SA
    -0.06
    (Menu
    -0.06
    Fi
    -0.06
    амп
    -0.06
    POSITIVE LOGITS
     architect
    0.08
     harass
    0.08
    Ack
    0.07
     Erotik
    0.07
     Spec
    0.07
     MainPage
    0.06
    cb
    0.06
     harassing
    0.06
    che
    0.06
     redux
    0.06
    Act Density 0.000%

    No Known Activations