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

    Neuronpedia

    INDEX
    Explanations

    fuck

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     य
    -0.08
     составе
    -0.08
     �
    -0.08
     bip
    -0.07
    y
    -0.07
    �
    -0.07
     Slee
    -0.07
     Cheng
    -0.06
     rez
    -0.06
     coy
    -0.06
    POSITIVE LOGITS
     FUCK
    0.07
     fuck
    0.07
    ██
    0.07
    >--
    0.06
     {}
    0.06
     massively
    0.06
    .calc
    0.06
    (__
    0.06
    _FM
    0.06
     Ensure
    0.06
    Act Density 0.006%

    No Known Activations