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

    Neuronpedia

    INDEX
    Explanations

    code and headers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mob
    -0.08
    (coord
    -0.08
    .bool
    -0.08
    (equal
    -0.08
     Been
    -0.07
    SENSOR
    -0.07
    .apple
    -0.07
     tweak
    -0.07
    /ng
    -0.07
     Buddh
    -0.07
    POSITIVE LOGITS
     dirname
    0.07
     ${↵
    0.07
    спеш
    0.07
    |$
    0.06
    تحقق
    0.06
     verdict
    0.06
     Noah
    0.06
    _POST
    0.06
     sen
    0.06
     pastoral
    0.06
    Act Density 0.040%

    No Known Activations