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

    Neuronpedia

    INDEX
    Explanations

    queries and expressions of thought or opinion

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

    Follows variations of the word "think" or "thought"

    np_acts-logits-general · gemini-2.0-flash

    think, thought, thinks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σθαι
    -0.77
     للمعارف
    -0.75
    -0.71
     Schengen
    -0.68
    }.
    -0.67
    ''')
    -0.66
    /−
    -0.66
    ſelves
    -0.65
    .";
    -0.64
    })*/
    -0.64
    POSITIVE LOGITS
     thinks
    0.80
     they
    0.74
     it
    0.74
     THINK
    0.74
     think
    0.70
     Think
    0.70
    Think
    0.67
     we
    0.64
     thought
    0.64
    think
    0.64
    Act Density 0.128%

    No Known Activations