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

    Neuronpedia

    INDEX
    Explanations

    utilization

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bimod
    0.65
    istosoma
    0.57
    ollary
    0.56
     Gastgeber
    0.56
    OGND
    0.55
    odiazep
    0.55
    <unused48>
    0.55
     modos
    0.54
    0.54
    बंधनाच्या
    0.54
    POSITIVE LOGITS
    util
    2.66
     util
    2.56
    Util
    2.20
     UTIL
    2.09
     utilization
    2.08
    UTIL
    2.08
     Util
    2.06
     Utilization
    1.94
    Utilization
    1.85
    利用
    1.76
    Act Density 0.058%

    No Known Activations