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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _language
    -0.07
    <th
    -0.07
     buổi
    -0.07
    	l
    -0.07
    oplayer
    -0.06
     Dissertation
    -0.06
    .tmp
    -0.06
    gan
    -0.06
    .bmp
    -0.06
    uator
    -0.06
    POSITIVE LOGITS
     Allied
    0.06
     handful
    0.06
     науков
    0.06
     Known
    0.06
    001
    0.06
    称
    0.06
     ^{
    0.06
     african
    0.06
    �
    0.06
     жод
    0.06
    Act Density 0.004%

    No Known Activations