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

    Neuronpedia

    INDEX
    Explanations

    Scientific paper introductions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Penis
    -0.08
    .machine
    -0.07
    innamon
    -0.07
     unlink
    -0.07
    .Decimal
    -0.07
     separators
    -0.07
    �
    -0.07
    naments
    -0.07
    ilenames
    -0.07
     pearls
    -0.07
    POSITIVE LOGITS
     CB
    0.07
     PC
    0.07
    居
    0.07
    طبع
    0.07
    screen
    0.07
    域
    0.07
    TC
    0.07
     MC
    0.07
    dh
    0.07
    邻
    0.06
    Act Density 0.005%

    No Known Activations