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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and connectors in lists or statements

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

    Appearing after parentheses, commas, and semicolons

    np_acts-logits-general · gemini-2.0-flash

    family members and biographical details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चीज़ों
    -0.37
    hyrchwyd
    -0.37
    Зноскі
    -0.34
    -------------</
    -0.33
    jooq
    -0.33
    welli
    -0.32
     betweenstory
    -0.32
     BoxFit
    -0.32
    expandindo
    -0.31
    台
    -0.31
    POSITIVE LOGITS
     auroit
    0.62
     pouvoit
    0.59
     feroit
    0.58
     enfans
    0.56
    consulté
    0.54
    enumii
    0.53
     réunis
    0.52
    étoit
    0.50
     plegable
    0.49
    writeFieldEnd
    0.49
    Act Density 0.010%

    No Known Activations