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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fashion
    -0.08
    Smarty
    -0.08
     לבין
    -0.07
    cles
    -0.07
    cross
    -0.07
    不合格
    -0.07
     pottery
    -0.07
    ,double
    -0.07
    (scanner
    -0.07
    꺄
    -0.07
    POSITIVE LOGITS
    相连
    0.07
     indicative
    0.06
    シーン
    0.06
    .utcnow
    0.06
     quest
    0.06
    選�
    0.06
    _deploy
    0.06
    ###↵
    0.06
    ирован
    0.06
     compounds
    0.06
    Act Density 0.000%

    No Known Activations