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
    paration
    -0.07
     prediction
    -0.07
    Bit
    -0.07
    asing
    -0.06
    婦
    -0.06
    امل
    -0.06
    set
    -0.06
    -insert
    -0.06
    .toByteArray
    -0.06
    цей
    -0.06
    POSITIVE LOGITS
     꿈
    0.07
     handjob
    0.07
     SAR
    0.07
    !)↵↵
    0.06
    	require
    0.06
    ？
    0.06
    форт
    0.06
     Hồng
    0.06
    .Flag
    0.06
     Vancouver
    0.06
    Act Density 0.006%

    No Known Activations