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

    Neuronpedia

    INDEX
    Explanations

    prompts for reflective thinking or encouraging contemplation

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

    think or imagine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.64
     initComponents
    -0.54
     الحره
    -0.52
    principalColumn
    -0.49
     يتيمه
    -0.49
    poem
    -0.47
    itinéraire
    -0.47
    帖最后由
    -0.46
    openzeppelin
    -0.46
    ramienta
    -0.45
    POSITIVE LOGITS
    Imagine
    0.56
    Remember
    0.48
     Imagine
    0.47
     remember
    0.46
     aDecoder
    0.40
    Recall
    0.40
    Consider
    0.40
     Remember
    0.39
     imagine
    0.39
     REMEMBER
    0.38
    Act Density 0.008%

    No Known Activations