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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mocked
    -0.07
     switches
    -0.07
     attaches
    -0.06
     overl
    -0.06
     selects
    -0.06
     assists
    -0.06
    _frontend
    -0.06
     MAN
    -0.06
     XCT
    -0.06
     найбіль
    -0.06
    POSITIVE LOGITS
     cuff
    0.06
    ´
    0.06
    엘
    0.06
     згідно
    0.06
    _outline
    0.06
     Haupt
    0.06
    过
    0.06
    reveal
    0.06
     Donovan
    0.06
    */
↵
    0.06
    Act Density 0.000%

    No Known Activations