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

    Neuronpedia

    INDEX
    Explanations

    If

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .authorization
    -0.06
    벤
    -0.06
    ensible
    -0.06
    Як
    -0.06
    idents
    -0.06
    -disable
    -0.06
     Glow
    -0.06
    rics
    -0.06
    тик
    -0.06
    елик
    -0.06
    POSITIVE LOGITS
     －
    0.07
     diff
    0.07
     –↵
    0.07
    ...)↵
    0.06
    :]↵↵
    0.06
    serir
    0.06
    Insert
    0.06
    Found
    0.06
     mantener
    0.06
    =context
    0.06
    Act Density 0.015%

    No Known Activations