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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uges
    -0.31
    ruption
    -0.29
    rlen
    -0.28
    enie
    -0.27
    å±Ģéķ¿
    -0.26
    zeichnet
    -0.25
    éĻIJåĪ¶
    -0.24
    arf
    -0.24
    å·¯
    -0.24
    rum
    -0.23
    POSITIVE LOGITS
    estate
    0.26
     Woman
    0.26
    ippi
    0.26
    Woman
    0.25
    å¼ĢåıijåĮº
    0.24
    é£İçŃĿ
    0.24
    =('
    0.24
    åīįéĶĭ
    0.23
    UDO
    0.23
    handled
    0.23
    Act Density 0.006%

    No Known Activations