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

    Neuronpedia

    INDEX
    Explanations

    elements related to progress, improvement, and negotiation processes

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

    learning, improving, or sharing

    np_acts-logits-general · gemini-2.0-flash

    actions like study, attack, negotiate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.78
     immemorial
    -0.62
    oredCriteria
    -0.62
     nakalista
    -0.57
    findpost
    -0.56
     EconPapers
    -0.56
     ModelExpression
    -0.55
    ("/:
    -0.54
    contentLoaded
    -0.54
    imageshack
    -0.52
    POSITIVE LOGITS
     the
    1.13
     throughout
    0.94
     from
    0.84
     a
    0.84
     with
    0.82
     without
    0.82
     beyond
    0.77
     alongside
    0.76
     extensively
    0.75
     aggressively
    0.73
    Act Density 0.878%

    No Known Activations