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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    างว
    -0.06
     Props
    -0.06
    "":
    -0.06
     /(
    -0.06
    ương
    -0.06
    $↵↵
    -0.06
     زد
    -0.06
    ा.↵
    -0.06
    (Transform
    -0.06
     هذا
    -0.06
    POSITIVE LOGITS
    PLEASE
    0.07
    DB
    0.07
    .groupControl
    0.07
    bler
    0.06
    _sun
    0.06
    Topic
    0.06
    Growing
    0.06
    database
    0.06
    _COMM
    0.06
    acom
    0.06
    Act Density 0.012%

    No Known Activations