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

    Neuronpedia

    INDEX
    Explanations

    aggregation, configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Concentration
    -0.82
     concentration
    -0.79
    WebVitals
    -0.74
    concentration
    -0.73
     Orientation
    -0.71
    orientation
    -0.67
     orientation
    -0.64
    GEBURTSDATUM
    -0.64
    WillAppear
    -0.59
     concentración
    -0.59
    POSITIVE LOGITS
    commodations
    0.66
     discs
    0.65
     disc
    0.62
    GetItem
    0.56
     sosis
    0.55
     disks
    0.54
     dí
    0.54
    setFlags
    0.54
    脚注の使い方
    0.53
    ције
    0.52
    Act Density 0.052%

    No Known Activations