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

    Neuronpedia

    INDEX
    Explanations

    intercept

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nivers
    -0.07
    'clock
    -0.07
    _GET
    -0.06
    这时候
    -0.06
    optic
    -0.06
    傧
    -0.06
    嫁给
    -0.06
    .navigate
    -0.06
     Majority
    -0.06
    _PKT
    -0.06
    POSITIVE LOGITS
    鳖
    0.07
     בתחום
    0.07
     Ж
    0.07
     Được
    0.07
     הקר
    0.07
     clave
    0.06
    ⾦
    0.06
    识别
    0.06
     הילדים
    0.06
    Trash
    0.06
    Act Density 0.009%

    No Known Activations