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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with Arabic heritage, especially relating to individuals and locations

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

    Tokens starting with "al", "el", or "Al"

    np_acts-logits-general · gemini-2.0-flash

    names with al prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -1.06
     pleaſure
    -1.02
     itſelf
    -1.01
    +#+#
    -0.96
     Theſe
    -0.95
     незавершена
    -0.95
     myſelf
    -0.94
     disambiguazione
    -0.94
     Anſ
    -0.93
     ſind
    -0.93
    POSITIVE LOGITS
     la
    0.89
     La
    0.87
    La
    0.80
     Le
    0.79
     De
    0.77
     Al
    0.76
     El
    0.72
     Del
    0.69
     le
    0.68
     Di
    0.68
    Act Density 0.072%

    No Known Activations