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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convin
    -0.08
     lyn
    -0.07
     displ
    -0.06
     Benson
    -0.06
     �
    -0.06
    れど
    -0.06
     mmc
    -0.06
    rpm
    -0.06
    _corr
    -0.06
    _pars
    -0.06
    POSITIVE LOGITS
     tamanho
    0.07
     chickens
    0.06
     :)↵
    0.06
     خود
    0.06
     心
    0.06
    _text
    0.06
     그녀
    0.06
     متوسط
    0.06
    icl
    0.06
    场
    0.06
    Act Density 0.000%

    No Known Activations