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

    Neuronpedia

    INDEX
    Explanations

    eliminated/out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setters
    -0.07
     MainAxisAlignment
    -0.07
     dia
    -0.07
    .Write
    -0.07
     kan
    -0.06
     barric
    -0.06
    Pen
    -0.06
    pto
    -0.06
     payer
    -0.06
     된다
    -0.06
    POSITIVE LOGITS
    ._↵
    0.07
    dub
    0.06
     Finding
    0.06
     dictates
    0.06
    атков
    0.06
     tý
    0.06
    wash
    0.06
    /Common
    0.05
    ,)↵
    0.05
     Newsletter
    0.05
    Act Density 0.008%

    No Known Activations