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

    Neuronpedia

    INDEX
    Explanations

    terms associated with measurements and performance metrics

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

    factor, life, clearance, return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.62
    المناصب
    -0.58
    AndEndTag
    -0.55
    LookAnd
    -0.52
    ConstraintMaker
    -0.51
    kloped
    -0.49
     gynhyrchwyd
    -0.49
     Infórmanos
    -0.48
    ACHUSET
    -0.47
    Rohy
    -0.46
    POSITIVE LOGITS
     brilho
    0.49
    AnchorTagHelper
    0.43
     variability
    0.43
     Komfort
    0.42
     uptime
    0.42
     seniority
    0.40
     etiquette
    0.40
     morale
    0.40
     scalability
    0.40
    coverage
    0.39
    Act Density 0.165%

    No Known Activations