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

    Neuronpedia

    INDEX
    Explanations

    Space distances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    儀
    -0.07
    лы
    -0.07
     *>
    -0.06
    /activity
    -0.06
    966
    -0.06
     come
    -0.06
    Fs
    -0.06
    Highlight
    -0.06
    Church
    -0.06
     ["
    -0.06
    POSITIVE LOGITS
     manifestations
    0.07
     ka
    0.07
    stup
    0.06
     Rib
    0.06
     coarse
    0.06
    _rom
    0.06
    >.↵↵
    0.06
    _UNDER
    0.06
     refinery
    0.06
     blatant
    0.06
    Act Density 0.013%

    No Known Activations