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

    Neuronpedia

    INDEX
    Explanations

    statements that indicate clarity or confirmation

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

    Statements of falsehood or rejection

    np_acts-logits-general · gemini-2.0-flash

    concession or contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.53
     متعلقه
    -0.52
    ftagPool
    -0.50
    хьтан
    -0.50
    TagHelper
    -0.48
    <>
    -0.47
    ügel
    -0.46
    ']
    -0.46
    Literatuur
    -0.45
     valueOf
    -0.44
    POSITIVE LOGITS
     despite
    1.02
    despite
    0.90
     regardless
    0.85
    regardless
    0.82
     irrespective
    0.81
     notwithstanding
    0.75
     несмотря
    0.72
     CreateTagHelper
    0.68
     Despite
    0.67
     apesar
    0.66
    Act Density 0.467%

    No Known Activations