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

    Neuronpedia

    INDEX
    Explanations

    usually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utsch
    -0.07
     pů
    -0.07
     scientifically
    -0.07
     президент
    -0.06
    κυ
    -0.06
    μβρίου
    -0.06
    stract
    -0.06
    ptom
    -0.06
     tai
    -0.06
    olla
    -0.06
    POSITIVE LOGITS
    Presentation
    0.06
     oe
    0.06
    れる
    0.06
    _RENDER
    0.06
    ')."
    0.06
    _MAKE
    0.06
     misdemean
    0.06
     زیر
    0.06
    .parsers
    0.06
     refl
    0.06
    Act Density 0.066%

    No Known Activations