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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and experiences

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

    I thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.66
    addContainerGap
    -0.46
     spalle
    -0.43
     ActivatedRoute
    -0.43
    eeq
    -0.40
    MemoryWarning
    -0.40
    Климат
    -0.40
     
    -0.39
     Vorsch
    -0.39
     inderdaad
    -0.39
    POSITIVE LOGITS
     thought
    1.83
    thought
    1.60
    Thought
    1.56
     Thought
    1.48
     decided
    1.38
     THOUGHT
    1.34
     figured
    1.21
     wanted
    1.21
     Decided
    1.16
    decided
    1.15
    Act Density 0.179%

    No Known Activations