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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )[
    -0.07
     pul
    -0.06
     hakk
    -0.06
    ')['
    -0.06
     comp
    -0.06
    )throws
    -0.06
     çalışan
    -0.06
     setUsername
    -0.06
    .ret
    -0.06
     flames
    -0.06
    POSITIVE LOGITS
    े।↵
    0.07
    _AES
    0.07
    _PRESS
    0.07
     Xbox
    0.06
    _increase
    0.06
     textures
    0.06
    Annual
    0.06
    490
    0.06
    REAM
    0.06
     works
    0.06
    Act Density 0.051%

    No Known Activations