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

    Neuronpedia

    INDEX
    Explanations

    percentages near 98%

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gallery
    -0.07
     filling
    -0.07
     implant
    -0.07
     decrypt
    -0.07
     tp
    -0.07
     expressed
    -0.06
     eliminar
    -0.06
    น
    -0.06
     treasury
    -0.06
    уз
    -0.06
    POSITIVE LOGITS
    _DEAD
    0.07
    ши
    0.07
    장을
    0.07
    (SELECT
    0.06
    ahat
    0.06
    ={!
    0.06
    camatan
    0.06
     voksne
    0.06
     ут
    0.06
    شة
    0.06
    Act Density 0.004%

    No Known Activations