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

    Neuronpedia

    INDEX
    Explanations

    mathematical/scientific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ори
    -0.08
     svensk
    -0.07
    textAlign
    -0.07
    hc
    -0.07
     sms
    -0.07
     divul
    -0.07
    association
    -0.07
    -repeat
    -0.07
    .isfile
    -0.07
    Tmp
    -0.07
    POSITIVE LOGITS
    的影响
    0.08
    Multip
    0.07
     pitch
    0.07
     Peyton
    0.07
     Playing
    0.07
     Cortex
    0.06
     Miy
    0.06
     correctness
    0.06
     Language
    0.06
     Tiền
    0.06
    Act Density 0.014%

    No Known Activations