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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ScreenWidth
    -0.06
     library
    -0.06
    .foundation
    -0.06
    ują
    -0.06
     Joy
    -0.06
     країн
    -0.06
    化
    -0.06
     countries
    -0.06
    .circular
    -0.06
     matrix
    -0.05
    POSITIVE LOGITS
    DTV
    0.07
     massac
    0.07
    تق
    0.07
     Ordering
    0.06
    +-+-+-+-
    0.06
     drifted
    0.06
    Refer
    0.06
    .registration
    0.06
    Ada
    0.06
    _sentence
    0.06
    Act Density 0.003%

    No Known Activations