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

    Neuronpedia

    INDEX
    Explanations

    Internet pages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teachers
    -0.07
    offline
    -0.07
     Groups
    -0.07
    Fs
    -0.07
    (coord
    -0.07
    icates
    -0.06
    endif
    -0.06
    漏
    -0.06
     reloading
    -0.06
     Dream
    -0.06
    POSITIVE LOGITS
     однако
    0.07
     Voldemort
    0.07
     hạt
    0.06
     Ori
    0.06
     JSONException
    0.06
     disgr
    0.06
     #$
    0.06
     misses
    0.06
     besten
    0.06
    Translated
    0.06
    Act Density 0.318%

    No Known Activations