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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and symbols

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

    New Zealand or specific locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.31
    EndGlobalSection
    -0.30
    ├──
    -0.28
     colonnes
    -0.28
    сунок
    -0.26
    “
    -0.25
    protected
    -0.24
     Są
    -0.24
    ɵɵelementStart
    -0.23
     dokumenta
    -0.23
    POSITIVE LOGITS
     الحره
    0.78
     '\\;'
    0.69
    новништво
    0.68
    rungsseite
    0.68
     שוליים
    0.68
    ंदीखरीदारी
    0.67
    󠁣
    0.66
    şam
    0.65
     nakalista
    0.64
    期刊论文
    0.63
    Act Density 0.036%

    No Known Activations