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

    Neuronpedia

    INDEX
    Explanations

    fill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     automation
    -0.07
     tiền
    -0.07
     Automation
    -0.07
    968
    -0.06
     dific
    -0.06
    kd
    -0.06
    庫
    -0.06
     vyžad
    -0.06
     Bast
    -0.06
    dık
    -0.06
    POSITIVE LOGITS
    PX
    0.06
    <Message
    0.06
    _EMPTY
    0.06
    illet
    0.06
     Murder
    0.06
     şey
    0.06
     specifying
    0.06
    -reaching
    0.06
    IFICATION
    0.06
    being
    0.06
    Act Density 0.000%

    No Known Activations