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

    Neuronpedia

    INDEX
    Explanations

    online

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     merciless
    -0.07
     か
    -0.07
    operand
    -0.06
     Diamonds
    -0.06
    редит
    -0.06
    敵
    -0.06
    stacles
    -0.06
     uranium
    -0.06
    Mad
    -0.06
     sonraki
    -0.06
    POSITIVE LOGITS
     showing
    0.07
     risult
    0.07
     stains
    0.07
     křes
    0.06
    يط
    0.06
     bitmap
    0.06
     kari
    0.06
     роботи
    0.06
     सल
    0.06
    ,’
    0.06
    Act Density 0.022%

    No Known Activations