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

    Neuronpedia

    INDEX
    Explanations

    situations involving significant emotional transitions or conflicts

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

    Punctuation, conjunctions, and certain symbols

    np_acts-logits-general · gemini-2.0-flash

    separating clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auffi
    -0.72
    Batis
    -0.69
     незавершена
    -0.68
    principalColumn
    -0.67
     الحره
    -0.66
     المعيارى
    -0.64
     daß
    -0.63
     fubject
    -0.62
     cref
    -0.62
     unſ
    -0.61
    POSITIVE LOGITS
     Whilst
    0.59
    Whilst
    0.57
     whilst
    0.55
     cho
    0.50
    Datuak
    0.49
     glaring
    0.49
    slowly
    0.48
     duh
    0.47
    ätzlich
    0.47
    慢慢的
    0.46
    Act Density 0.074%

    No Known Activations