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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LastName
    -0.06
    (ct
    -0.06
    _mix
    -0.06
     foreground
    -0.06
    _ne
    -0.06
    NE
    -0.06
    Empty
    -0.06
     task
    -0.06
    _features
    -0.06
     honored
    -0.06
    POSITIVE LOGITS
     autism
    0.07
    σιμοποι
    0.06
     müşteri
    0.06
    ीण
    0.06
    ısının
    0.06
     strangers
    0.06
    mayan
    0.06
    adden
    0.06
     район
    0.06
    φερ
    0.06
    Act Density 0.066%

    No Known Activations