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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ine"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bry
    -0.07
    roc
    -0.07
    (R
    -0.07
    Spatial
    -0.06
     dyn
    -0.06
    	java
    -0.06
     d
    -0.06
    _Init
    -0.06
     使用
    -0.06
     simplify
    -0.06
    POSITIVE LOGITS
    心意
    0.07
    نم
    0.07
     headings
    0.07
     whiteColor
    0.07
    -condition
    0.07
     unsett
    0.07
    平常
    0.07
    鹇
    0.07
     heir
    0.06
    /settings
    0.06
    Act Density 0.001%

    No Known Activations