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

    Neuronpedia

    INDEX
    Explanations

    YORK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    建
    -0.28
    lagen
    -0.25
    äºĨ解ä¸Ģä¸ĭ
    -0.24
    ç¢İ
    -0.24
    æ²Ļ
    -0.24
    _bw
    -0.24
    ogene
    -0.24
    宿
    -0.23
    群
    -0.23
    .ModelForm
    -0.23
    POSITIVE LOGITS
     Strategies
    0.27
    æĻħ
    0.26
    楣
    0.25
    zers
    0.24
    æĴŀ
    0.24
    ?id
    0.24
    åºĶ对
    0.24
    èĬ±åĽŃ
    0.24
    t
    0.24
    tom
    0.24
    Act Density 0.039%

    No Known Activations