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

    Neuronpedia

    INDEX
    Explanations

    commands or prompts to think critically and reflectively

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

    "Think" followed by "about."

    np_acts-logits-general · gemini-2.0-flash

    thinking about something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.66
    otras
    -0.65
     forState
    -0.65
    ttino
    -0.64
    posedge
    -0.64
    principalColumn
    -0.63
    NewLabel
    -0.63
    RepeatedField
    -0.63
    èlement
    -0.62
    ddots
    -0.62
    POSITIVE LOGITS
     about
    1.18
     think
    0.96
    Think
    0.95
     THINK
    0.92
     Think
    0.91
     thinks
    0.89
    think
    0.87
     thoughts
    0.84
     thought
    0.75
    about
    0.74
    Act Density 0.073%

    No Known Activations