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

    Neuronpedia

    INDEX
    Explanations

    references to case studies and reports within academic literature

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

    quantity or majority

    np_acts-logits-general · gemini-2.0-flash

    listing conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }>;
    -0.59
    libft
    -0.55
    ########.
    -0.54
    ukone
    -0.52
    __*/
    -0.52
     betweenstory
    -0.48
    )]=
    -0.46
    osoba
    -0.46
    енча
    -0.46
    джет
    -0.46
    POSITIVE LOGITS
     none
    1.75
     plupart
    1.65
     maioria
    1.56
     mayoría
    1.55
    none
    1.53
     None
    1.50
    None
    1.48
    どれも
    1.47
     большинство
    1.43
     kebanyakan
    1.42
    Act Density 1.057%

    No Known Activations