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

    Neuronpedia

    INDEX
    Explanations

    abbreviation IR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lenker
    -0.82
    AndEndTag
    -0.79
    OGND
    -0.79
    URLException
    -0.76
    IntoConstraints
    -0.76
     IR
    -0.75
    Autoritní
    -0.71
    SourceChecksum
    -0.70
    findpost
    -0.69
     transfieras
    -0.66
    POSITIVE LOGITS
    fos
    0.55
    UMNS
    0.53
    റ്
    0.52
     hor
    0.50
     Horizon
    0.48
     cer
    0.48
     Sel
    0.48
    phos
    0.48
    ExecutionContext
    0.48
    klä
    0.48
    Act Density 0.107%

    No Known Activations