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

    Neuronpedia

    INDEX
    Explanations

    coding syntax and structure related to prefixes and configuration in programming contexts

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

    prefix increment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TType
    -0.42
    PYX
    -0.37
    tagez
    -0.36
    HideFlags
    -0.35
    MessageTagHelper
    -0.35
    SequentialGroup
    -0.35
    kloped
    -0.34
     ModelRenderer
    -0.34
     Jud
    -0.34
    NullCheck
    -0.34
    POSITIVE LOGITS
     prefix
    0.98
     Prefix
    0.96
    prefix
    0.95
     prefixes
    0.87
    Prefix
    0.87
     PREFIX
    0.83
    PREFIX
    0.80
    prefixes
    0.78
     prefixed
    0.56
     suffix
    0.54
    Act Density 0.022%

    No Known Activations