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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tC
    -0.07
    aku
    -0.07
    AVED
    -0.06
    因
    -0.06
     factions
    -0.06
     Minneapolis
    -0.06
    _DEST
    -0.06
     condu
    -0.06
    "`↵
    -0.06
     Partition
    -0.06
    POSITIVE LOGITS
    수의
    0.07
     золот
    0.06
     Pivot
    0.06
     통합
    0.06
    atitis
    0.06
    Activated
    0.06
    storybook
    0.06
    ології
    0.06
    prung
    0.06
     border
    0.06
    Act Density 0.006%

    No Known Activations