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

    Neuronpedia

    INDEX
    Explanations

    reasoning and justification

    np_max-act · gemini-2.0-flash

    words and short phrases that signal reasoning, cause, or discourse-connective (explanatory/contrasting) structure.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     scandal
    -0.06
    	signal
    -0.06
     driven
    -0.06
     Charger
    -0.06
     الميلاد
    -0.06
     Sergio
    -0.06
     جزء
    -0.06
    ским
    -0.06
    .Resolve
    -0.06
     princes
    -0.06
    POSITIVE LOGITS
    군요
    0.07
     花
    0.07
     ROS
    0.06
     речі
    0.06
     เท
    0.06
    đ
    0.06
    cljs
    0.06
    �
    0.06
     je
    0.06
    ξεις
    0.06
    Act Density 0.125%

    No Known Activations