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

    Neuronpedia

    INDEX
    Explanations

    equity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breathe
    -0.07
     Atlas
    -0.06
     حافظ
    -0.06
     alertController
    -0.06
    forgot
    -0.06
    getResponse
    -0.06
    Mui
    -0.06
     bile
    -0.06
    -parse
    -0.06
     Got
    -0.06
    POSITIVE LOGITS
    MERCHANTABILITY
    0.08
    ি
    0.07
    COMMENT
    0.07
     grouped
    0.07
    Edge
    0.06
     �
    0.06
     ){
↵
    0.06
    ?)↵↵
    0.06
     Quite
    0.06
     Rh
    0.06
    Act Density 0.001%

    No Known Activations