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

    Neuronpedia

    INDEX
    Explanations

    sale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     productivity
    -0.07
    .Activity
    -0.07
     stupidity
    -0.07
    .BufferedReader
    -0.07
     Heavy
    -0.07
    および
    -0.07
    CBS
    -0.07
    /Z
    -0.06
    obox
    -0.06
     عص
    -0.06
    POSITIVE LOGITS
     Sale
    0.11
     sale
    0.09
    Sale
    0.08
    ату
    0.07
     SALE
    0.07
     tc
    0.07
     Tale
    0.07
    ание
    0.07
    alo
    0.07
    atoire
    0.07
    Act Density 0.007%

    No Known Activations