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

    Neuronpedia

    INDEX
    Explanations

    Broad topics and lists

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    .↵
    -0.10
    size
    -0.09
    ↵
    -0.09
    Path
    -0.08
    ↵↵
    -0.08
    ↵
    -0.08
    。↵
    -0.08
    called
    -0.08
     enforcement
    -0.08
    ilde
    -0.07
    POSITIVE LOGITS
    ('/')[-
    0.07
    ちゃん
    0.07
    VALID
    0.06
    Newsletter
    0.06
    活得
    0.06
    TextLabel
    0.06
    のではない
    0.06
    _filled
    0.06
    موضوع
    0.06
    ༺
    0.06
    Act Density 0.122%

    No Known Activations