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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critical and logical thinking processes

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

    different ways of thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bar
    -0.34
    DateTimeField
    -0.33
     ROUTES
    -0.31
     Eccl
    -0.31
     Usher
    -0.31
     Harvest
    -0.30
     invokingState
    -0.30
     Tapes
    -0.30
    TokenNameEQUAL
    -0.29
     лето
    -0.29
    POSITIVE LOGITS
     thinking
    0.98
    thinking
    0.98
    Thinking
    0.94
     Thinking
    0.92
     pensamiento
    0.91
    思维
    0.85
     Denken
    0.82
     berpikir
    0.82
    思考
    0.80
     thinker
    0.79
    Act Density 0.098%

    No Known Activations