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

    Neuronpedia

    INDEX
    Explanations

    contrasting opinions/examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afflict
    -0.07
    算
    -0.07
    hm
    -0.07
     Cookies
    -0.07
    сы
    -0.06
    raf
    -0.06
     tu
    -0.06
     Charges
    -0.06
    iks
    -0.06
    173
    -0.06
    POSITIVE LOGITS
     ~(
    0.07
    .Raise
    0.06
     uber
    0.06
    ----------↵↵
    0.06
    ALIGN
    0.06
    였다
    0.06
     Julio
    0.06
     ​
    0.06
    سمة
    0.06
     Align
    0.06
    Act Density 0.040%

    No Known Activations