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

    Neuronpedia

    INDEX
    Explanations

    extension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PointSize
    -0.07
    _cs
    -0.07
     Increase
    -0.07
    _solve
    -0.07
    .Import
    -0.07
    _DISABLE
    -0.07
    ีย
    -0.06
    _DETECT
    -0.06
     др
    -0.06
    VISIBLE
    -0.06
    POSITIVE LOGITS
    際
    0.07
    ulously
    0.06
    ньо
    0.06
    /ad
    0.06
     proposition
    0.06
    Below
    0.06
    Looks
    0.06
     charged
    0.06
    VERTISEMENT
    0.06
    ленных
    0.06
    Act Density 0.027%

    No Known Activations