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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kür
    -0.07
     هر
    -0.06
     veins
    -0.06
     Gaga
    -0.06
     paradise
    -0.06
     tienes
    -0.06
     Char
    -0.06
     (/
    -0.06
     CY
    -0.06
    Manchester
    -0.06
    POSITIVE LOGITS
    -il
    0.07
    _BC
    0.07
     getObject
    0.07
    ­ing
    0.07
     SplashScreen
    0.07
    ']));↵
    0.07
     HelloWorld
    0.07
    .horizontal
    0.06
     "));↵
    0.06
    _IMP
    0.06
    Act Density 0.009%

    No Known Activations