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

    Neuronpedia

    INDEX
    Explanations

    named

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chun
    -0.07
     talks
    -0.07
    海关
    -0.07
    pg
    -0.07
    existence
    -0.07
    szedł
    -0.06
    一个个
    -0.06
    security
    -0.06
    恩
    -0.06
     ],↵↵
    -0.06
    POSITIVE LOGITS
     addObserver
    0.07
     presentViewController
    0.07
     sanitize
    0.07
    .icons
    0.07
    _utf
    0.07
     AJAX
    0.07
     kullanılan
    0.07
    IBAction
    0.07
    欤
    0.06
    ollapsed
    0.06
    Act Density 0.009%

    No Known Activations