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

    Neuronpedia

    INDEX
    Explanations

    phrases that express clarity and thoughtful consideration

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

    thinking differently and together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.46
     undef
    -0.46
     allegedly
    -0.44
     VIDEOTAPE
    -0.44
    SpringRunner
    -0.41
    seam
    -0.41
     Odor
    -0.40
    gabe
    -0.40
     offer
    -0.40
    lankton
    -0.40
    POSITIVE LOGITS
    Thinking
    1.10
     thinking
    1.10
     Thinking
    1.03
    Think
    1.02
    thinking
    1.00
     Think
    1.00
     THINK
    1.00
     pensamiento
    0.98
    THINK
    0.97
     think
    0.94
    Act Density 0.019%

    No Known Activations