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

    Neuronpedia

    INDEX
    Explanations

    references to names and titles

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

    words like "named" or "called"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.62
    Искәрмәләр
    -0.45
    -0.45
    PerformLayout
    -0.43
    kmale
    -0.38
     contigo
    -0.38
    stdarg
    -0.37
    ValueGenerated
    -0.37
    });*/
    -0.36
     بيها
    -0.36
    POSITIVE LOGITS
     prosa
    0.94
     fancy
    0.80
     glamorous
    0.72
    fancy
    0.71
     cute
    0.68
     mundane
    0.67
     catchy
    0.64
     banal
    0.64
     Sounds
    0.64
     mouthful
    0.63
    Act Density 0.067%

    No Known Activations