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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    (label
    -0.07
    _CTL
    -0.07
     aides
    -0.07
    Ngày
    -0.06
     deux
    -0.06
     Clock
    -0.06
     MMI
    -0.06
    _N
    -0.06
     Element
    -0.06
    POSITIVE LOGITS
     Historic
    0.07
    .iloc
    0.06
    sharp
    0.06
    .ptr
    0.06
     everybody
    0.06
     acid
    0.06
    -www
    0.06
    .species
    0.06
     Při
    0.06
     itu
    0.06
    Act Density 0.019%

    No Known Activations