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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     záv
    -0.08
    �
    -0.07
    -called
    -0.07
    ,$_
    -0.07
    riere
    -0.06
    ари
    -0.06
    セ
    -0.06
    (OS
    -0.06
    -sort
    -0.06
    교육
    -0.06
    POSITIVE LOGITS
    forcement
    0.06
    _fast
    0.06
    '",↵
    0.06
    ingle
    0.06
     KIND
    0.06
     Ultra
    0.06
     Brake
    0.06
    HBoxLayout
    0.06
    (Exception
    0.06
    .Tasks
    0.06
    Act Density 0.000%

    No Known Activations