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

    Neuronpedia

    INDEX
    Explanations

    various types of punctuation and syntax constructs in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or names containing abbreviations

    np_acts-logits-general · gemini-2.0-flash

    robustness of NGS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     em
    -0.50
     die
    -0.50
    LoginComponent
    -0.48
     HttpNotFound
    -0.43
     Great
    -0.41
    rä
    -0.41
    TabIndex
    -0.41
     sur
    -0.40
     enough
    -0.40
    合
    -0.40
    POSITIVE LOGITS
    LookAnd
    0.91
    Portale
    0.85
     myſelf
    0.83
    MLLoader
    0.80
     scattata
    0.77
     ſche
    0.74
     picioare
    0.73
     Houſe
    0.73
    WriteTagHelper
    0.73
     leſs
    0.73
    Act Density 0.157%

    No Known Activations