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

    Neuronpedia

    INDEX
    Explanations

    structures and syntactical patterns related to programming code, particularly those that define or render UI components

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

    Code snippets or code-like structures

    np_acts-logits-general · gemini-2.0-flash

    profile data, HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.71
    ","");
    -0.60
     vPvB
    -0.60
     '\\;'
    -0.60
     ')
    -0.57
    PhysRevD
    -0.56
     ");
    -0.56
     "
    -0.56
    DeleteBehavior
    -0.56
     '
    -0.55
    POSITIVE LOGITS
    !!
    0.78
    __(/*!
    0.70
    !
    0.69
     !!
    0.68
    !(
    0.66
    props
    0.65
    (!
    0.64
    !</
    0.63
    !}
    0.63
    !!!
    0.61
    Act Density 0.028%

    No Known Activations