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

    Neuronpedia

    INDEX
    Explanations

    Code and error messages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    寂
    -0.08
    áb
    -0.07
    ��
    -0.07
    bul
    -0.07
    יץ
    -0.07
    踽
    -0.07
    abay
    -0.07
    .reply
    -0.07
    DataURL
    -0.07
     tabPage
    -0.06
    POSITIVE LOGITS
    ，↵
    0.07
     sagen
    0.07
     Slack
    0.06
    国足
    0.06
     niezbędn
    0.06
     ||↵
    0.06
    袜
    0.06
     intim
    0.06
    dług
    0.06
    -leg
    0.06
    Act Density 0.002%

    No Known Activations