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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decision-making and legal processes

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

    Punctuation followed by a transition word

    np_acts-logits-general · gemini-2.0-flash

    contrast or elaboration after a clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    -0.53
     <<<<<<<<<<<<<<
    -0.52
    ThroughAttribute
    -0.50
     consists
    -0.47
    ().
    -0.47
     pewno
    -0.47
    دانشنامهٔ
    -0.47
     contains
    -0.47
    ativement
    -0.47
    dessous
    -0.47
    POSITIVE LOGITS
     referenties
    0.62
     faute
    0.59
    addPreferredGap
    0.57
     besides
    0.57
    ServletException
    0.55
     distanciation
    0.54
    ighed
    0.54
    πει
    0.54
     الرياضيه
    0.53
     somewhat
    0.52
    Act Density 0.227%

    No Known Activations