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

    Neuronpedia

    INDEX
    Explanations

    computer networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _slug
    -0.07
    paths
    -0.06
    -bed
    -0.06
     واب
    -0.06
    Retrieve
    -0.06
    useum
    -0.06
     maritime
    -0.06
     offen
    -0.06
    位
    -0.06
    .reward
    -0.06
    POSITIVE LOGITS
    .IP
    0.07
     vmin
    0.07
     xyz
    0.06
    _credit
    0.06
    POCH
    0.06
    usted
    0.06
     nhanh
    0.06
     setState
    0.06
     Theo
    0.06
    omination
    0.06
    Act Density 0.023%

    No Known Activations