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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illo
    -0.07
    Cached
    -0.07
     imagen
    -0.06
    (det
    -0.06
    -stat
    -0.06
    .getActivity
    -0.06
    .setting
    -0.06
    (ele
    -0.06
    //'
    -0.06
     explaining
    -0.06
    POSITIVE LOGITS
     киш
    0.06
     خلف
    0.06
     вив
    0.06
     зустрі
    0.06
     masturbation
    0.06
    URRENT
    0.06
    "os
    0.06
    anglicky
    0.06
     чист
    0.06
    _resume
    0.06
    Act Density 0.002%

    No Known Activations