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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SCRIPT
    -0.07
    _idx
    -0.07
    dzą
    -0.07
     król
    -0.07
    EXP
    -0.07
    帝王
    -0.07
    حلول
    -0.07
    _deleted
    -0.07
    صديق
    -0.07
    jec
    -0.07
    POSITIVE LOGITS
    hest
    0.08
    (dic
    0.07
    (ray
    0.07
    ernational
    0.07
     Darren
    0.07
    ++){
    0.07
    (height
    0.07
    .onResume
    0.06
     celery
    0.06
    nested
    0.06
    Act Density 0.414%

    No Known Activations