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

    Neuronpedia

    INDEX
    Explanations

    Nan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ingr
    -0.07
    �
    -0.07
     hinder
    -0.06
    ทาง
    -0.06
    ;)
    -0.06
     Beer
    -0.06
     tokenId
    -0.06
     bakımından
    -0.06
     lender
    -0.06
     ferm
    -0.06
    POSITIVE LOGITS
    рать
    0.07
     proyectos
    0.07
    (Control
    0.06
    ח
    0.06
     snaží
    0.06
    امت
    0.06
    ۰
    0.06
    ός
    0.06
     einige
    0.06
    ické
    0.06
    Act Density 0.006%

    No Known Activations