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

    Neuronpedia

    INDEX
    Explanations

    Updates/announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icontrol
    -0.07
     autof
    -0.06
    aires
    -0.06
     Zuk
    -0.06
    牛
    -0.06
    _Cancel
    -0.06
    elfast
    -0.06
     Cecil
    -0.06
    ihar
    -0.06
    ondere
    -0.06
    POSITIVE LOGITS
    .bo
    0.07
    .dom
    0.06
     wrench
    0.06
    дан
    0.06
    .Matrix
    0.06
     modified
    0.06
     enhances
    0.06
    _extraction
    0.06
     about
    0.06
    Att
    0.06
    Act Density 0.007%

    No Known Activations