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

    Neuronpedia

    INDEX
    Explanations

    code structure and control flow keywords

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

    Code that returns boolean values

    np_acts-logits-general · gemini-2.0-flash

    returning boolean expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.68
     userSchema
    -0.65
     WaitForSeconds
    -0.63
    yntaxException
    -0.63
     ""],
    -0.61
     bezeichneter
    -0.61
    StructEnd
    -0.60
    ']?>
    -0.58
    malink
    -0.57
    ']='
    -0.57
    POSITIVE LOGITS
     !(
    1.06
     !
    0.96
     ((
    0.81
     (
    0.81
     (!(
    0.79
    !(
    0.75
     !!
    0.73
    (!(
    0.71
     (!
    0.69
    (!
    0.67
    Act Density 0.198%

    No Known Activations