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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    И
    -0.06
     MEMORY
    -0.06
    ันเป
    -0.06
     synthes
    -0.06
    уки
    -0.06
    �
    -0.06
     Banana
    -0.06
     shrimp
    -0.06
    (&$
    -0.06
    ghest
    -0.06
    POSITIVE LOGITS
     interpolate
    0.07
    "http
    0.07
    _precision
    0.07
    有关
    0.07
    -admin
    0.06
    .StackTrace
    0.06
    ss
    0.06
     extr
    0.06
    台
    0.06
    SC
    0.06
    Act Density 0.000%

    No Known Activations