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

    Neuronpedia

    INDEX
    Explanations

    Code/formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.88
     propOrder
    -0.84
    AccessorTable
    -0.84
    LookAnd
    -0.82
    enumii
    -0.82
     IBOutlet
    -0.81
    -0.79
     snippetHide
    -0.79
    SourceChecksum
    -0.79
    ьаж
    -0.75
    POSITIVE LOGITS
    iec
    0.39
     god
    0.39
     kyl
    0.37
     Bat
    0.35
    કા
    0.35
     Пре
    0.35
    Пре
    0.35
    Bat
    0.34
    Dec
    0.34
     hånd
    0.34
    Act Density 0.001%

    No Known Activations