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

    Neuronpedia

    INDEX
    Explanations

    Places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     physician
    -0.08
    (Yii
    -0.08
     pian
    -0.08
    Exclusive
    -0.08
    (egt
    -0.07
    (expr
    -0.07
    韭
    -0.07
     filler
    -0.07
     washer
    -0.07
     рецеп
    -0.07
    POSITIVE LOGITS
    开放
    0.07
    .stage
    0.07
    ences
    0.06
    	grid
    0.06
     unst
    0.06
    斓
    0.06
    arsers
    0.06
     Fallen
    0.06
    远离
    0.06
    bounded
    0.06
    Act Density 0.083%

    No Known Activations