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

    Neuronpedia

    INDEX
    Explanations

    whitespace and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hel
    -0.06
     disco
    -0.06
    _mobile
    -0.06
    Helper
    -0.06
    Vis
    -0.06
    φέ
    -0.06
     Mik
    -0.06
    ~~~~~~~~~~~~~~~~
    -0.06
     DWORD
    -0.06
     hear
    -0.06
    POSITIVE LOGITS
    alore
    0.07
     muse
    0.06
     elim
    0.06
    anc
    0.06
     seller
    0.06
    UCH
    0.06
     recent
    0.06
    сон
    0.06
    \<^
    0.06
     skincare
    0.06
    Act Density 0.031%

    No Known Activations