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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Qualified
    -0.06
    .cod
    -0.06
     tisíc
    -0.06
    /category
    -0.06
     Dollars
    -0.06
     APIs
    -0.06
    sWith
    -0.06
    ROP
    -0.06
     srpna
    -0.06
    __[
    -0.06
    POSITIVE LOGITS
     BI
    0.06
    ogr
    0.06
    里
    0.06
     GK
    0.06
     messed
    0.06
    xb
    0.06
    ็ค
    0.06
     tt
    0.06
     genuinely
    0.06
    fell
    0.06
    Act Density 0.057%

    No Known Activations