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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Yaw
    -0.07
     McCartney
    -0.07
    ToEnd
    -0.06
    utedString
    -0.06
     Joanna
    -0.06
    Selectors
    -0.06
    ContainerGap
    -0.06
     Twitter
    -0.06
     McCain
    -0.06
    ==========
    -0.06
    POSITIVE LOGITS
    false
    0.06
    piel
    0.06
     habit
    0.06
     PRO
    0.06
     PAR
    0.06
    .ToList
    0.06
     PU
    0.06
    cuador
    0.06
    ',"
    0.06
    .Int
    0.06
    Act Density 0.000%

    No Known Activations