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

    Neuronpedia

    INDEX
    Explanations

    Sorting code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '{}
    -0.07
     "',
    -0.07
     cites
    -0.06
    ),'
    -0.06
     albeit
    -0.06
     Sec
    -0.06
    multi
    -0.06
     %.
    -0.06
    OTP
    -0.06
    ('>
    -0.06
    POSITIVE LOGITS
    REP
    0.07
    ái
    0.07
    ichte
    0.07
     currentState
    0.06
    _spectrum
    0.06
     Gard
    0.06
    airo
    0.06
    Promise
    0.06
    تق
    0.06
    RELATED
    0.06
    Act Density 0.011%

    No Known Activations