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

    Neuronpedia

    INDEX
    Explanations

    structural elements in text or code

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

    foreign language and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.77
     CreateTagHelper
    -0.70
     <<<<<<<<<<<<<<
    -0.64
    tagHelperRunner
    -0.64
     betweenstory
    -0.63
     Infórmanos
    -0.63
    adaptiveStyles
    -0.63
     NSCoder
    -0.63
    GraphicsUnit
    -0.61
    OGND
    -0.60
    POSITIVE LOGITS
     Blatt
    0.50
    The
    0.43
     felicità
    0.43
     “
    0.43
     Kreuz
    0.42
    Basic
    0.41
     Kaufmann
    0.41
    etCode
    0.40
     Aufstieg
    0.40
     felicidade
    0.40
    Act Density 0.001%

    No Known Activations