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

    Neuronpedia

    INDEX
    Explanations

    line punch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чя
    -0.07
    �
    -0.07
     manžel
    -0.06
    荒
    -0.06
     Penal
    -0.06
    閉
    -0.06
    -digit
    -0.06
    лых
    -0.06
     gần
    -0.06
    pedo
    -0.06
    POSITIVE LOGITS
     sendMessage
    0.07
    uplicates
    0.06
    structure
    0.06
     filename
    0.06
     sings
    0.06
     것이다
    0.06
    Eng
    0.06
    RESULTS
    0.06
    ្�
    0.06
    Wait
    0.06
    Act Density 0.004%

    No Known Activations