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

    Neuronpedia

    INDEX
    Explanations

    exception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    úc
    -0.07
    Ĭ
    -0.07
    (My
    -0.07
     WTO
    -0.06
    _UID
    -0.06
    (chan
    -0.06
    ckett
    -0.06
    帖
    -0.06
    y
    -0.06
    IMG
    -0.06
    POSITIVE LOGITS
     atrocities
    0.07
    تدخل
    0.07
    resource
    0.07
     behaving
    0.07
    사를
    0.07
    ально
    0.06
    专项
    0.06
    始终
    0.06
     sowie
    0.06
    直升
    0.06
    Act Density 0.004%

    No Known Activations