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

    Neuronpedia

    INDEX
    Explanations

    Describing aspects or qualities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recurs
    -0.07
    (Be
    -0.07
     tracing
    -0.07
     notre
    -0.06
    地区
    -0.06
    _sn
    -0.06
     уст
    -0.06
    To
    -0.06
    Mono
    -0.06
     Tyto
    -0.06
    POSITIVE LOGITS
    sgi
    0.07
    ician
    0.06
    _bins
    0.06
    breaker
    0.06
    IONS
    0.06
    ов
    0.06
     jaz
    0.06
    dater
    0.06
     mur
    0.06
    terms
    0.06
    Act Density 0.057%

    No Known Activations