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

    Neuronpedia

    INDEX
    Explanations

    references to reasoning, thought, and differing perspectives regarding competence and decisions

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

    reasonable minds could differ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.47
    HideFlags
    -0.41
     usur
    -0.39
     lega
    -0.38
     <=",
    -0.38
    AndView
    -0.37
     Lightboxes
    -0.36
     meshes
    -0.36
     Leg
    -0.35
    icitis
    -0.35
    POSITIVE LOGITS
    RectangleBorder
    0.60
     BorderSide
    0.49
    InputBorder
    0.49
     freiw
    0.45
     vrijwilli
    0.43
    elemField
    0.41
    addComponent
    0.40
     pracov
    0.40
     respected
    0.39
     expertos
    0.39
    Act Density 0.420%

    No Known Activations