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

    Neuronpedia

    INDEX
    Explanations

    explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nergy
    -0.07
    dep
    -0.07
     Mansion
    -0.06
    -reader
    -0.06
    uitar
    -0.06
    нят
    -0.06
    rž
    -0.06
    nothing
    -0.06
     LIMITED
    -0.06
    attempt
    -0.06
    POSITIVE LOGITS
     fileList
    0.07
    itra
    0.06
    Cİ
    0.06
    ToFile
    0.06
    HEET
    0.06
    晓
    0.06
    �
    0.06
    	is
    0.06
     přím
    0.06
     кал
    0.06
    Act Density 0.158%

    No Known Activations