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

    Neuronpedia

    INDEX
    Explanations

    clarify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.52
    IBOutlet
    -0.52
    Low
    -0.49
    PYX
    -0.46
    low
    -0.46
    jspb
    -0.46
    sizeCache
    -0.45
    TemporalType
    -0.45
     Low
    -0.44
     low
    -0.43
    POSITIVE LOGITS
    apimachinery
    0.74
     confusion
    0.65
    VersionUID
    0.63
    atomy
    0.61
     matters
    0.61
     misunderstand
    0.59
    exitRule
    0.59
    Cordialement
    0.58
     misconceptions
    0.58
     rumours
    0.58
    Act Density 0.003%

    No Known Activations