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

    Neuronpedia

    INDEX
    Explanations

    permits and restrictions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .httpClient
    -0.07
    _lookup
    -0.07
    spread
    -0.07
    tcp
    -0.07
     CLOSED
    -0.06
    PHPUnit
    -0.06
    setTimeout
    -0.06
     Celtic
    -0.06
     Москва
    -0.06
    iffin
    -0.06
    POSITIVE LOGITS
    残
    0.07
    兼具
    0.06
    ше
    0.06
    _rad
    0.06
     gun
    0.06
    га
    0.06
     stronger
    0.06
    患
    0.06
    猎
    0.06
    变革
    0.06
    Act Density 0.126%

    No Known Activations