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

    Neuronpedia

    INDEX
    Explanations

    requests for assistance or support

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

    offering assistance or support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isielt
    -0.46
    éen
    -0.42
    guides
    -0.42
    ěn
    -0.42
    Guides
    -0.42
     olvido
    -0.41
     Мексичка
    -0.41
    ➯
    -0.41
    éens
    -0.40
    ⎩
    -0.40
    POSITIVE LOGITS
     effort
    0.54
     efforts
    0.50
     spread
    0.50
     الحره
    0.47
     spreading
    0.46
     achieving
    0.44
     sustaining
    0.43
     accomplishing
    0.43
    Effort
    0.42
     Efforts
    0.41
    Act Density 0.013%

    No Known Activations