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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     splits
    -0.07
     calls
    -0.07
     Robbins
    -0.07
     intellectual
    -0.07
    Fs
    -0.07
     anger
    -0.06
    means
    -0.06
     sensible
    -0.06
     project
    -0.06
     dark
    -0.06
    POSITIVE LOGITS
    iterr
    0.07
     chac
    0.07
    цик
    0.06
    /rem
    0.06
     سف
    0.06
    ationale
    0.06
     ㅇㅇ
    0.06
    렌
    0.06
    (ierr
    0.06
     пів
    0.06
    Act Density 0.013%

    No Known Activations