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

    Neuronpedia

    INDEX
    Explanations

    Algebraic expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ад
    -0.07
     tải
    -0.07
     died
    -0.07
     pain
    -0.06
    pictures
    -0.06
    opping
    -0.06
    _images
    -0.06
    ую
    -0.06
    ulsive
    -0.06
     Park
    -0.06
    POSITIVE LOGITS
    	LOGGER
    0.09
    (rowIndex
    0.07
     INC
    0.07
    .FR
    0.07
     instr
    0.06
     QIcon
    0.06
    _axes
    0.06
     Nass
    0.06
     Prel
    0.06
    stddef
    0.06
    Act Density 0.033%

    No Known Activations