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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getWindow
    -0.06
    (sent
    -0.06
    �
    -0.06
     VID
    -0.06
     فروش
    -0.06
     иг
    -0.06
     contradictory
    -0.05
    '))
    -0.05
    horia
    -0.05
    .assertEquals
    -0.05
    POSITIVE LOGITS
     Adam
    0.09
    Adam
    0.07
     замет
    0.07
    Aggregate
    0.07
     text
    0.07
    	create
    0.07
    figures
    0.06
    rade
    0.06
    filename
    0.06
    .rar
    0.06
    Act Density 0.001%

    No Known Activations