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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ений
    -0.07
     Dann
    -0.07
    ранения
    -0.06
     King
    -0.06
     logout
    -0.06
    ennessee
    -0.06
    __))
    -0.06
    orting
    -0.06
     Embassy
    -0.06
     KING
    -0.06
    POSITIVE LOGITS
     बज
    0.07
    Accessory
    0.06
     clearTimeout
    0.06
     청
    0.06
    ूछ
    0.06
    �
    0.06
    IENTATION
    0.06
    uplic
    0.06
    >.↵↵
    0.06
     HTC
    0.06
    Act Density 0.005%

    No Known Activations