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

    Neuronpedia

    INDEX
    Explanations

    following text examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     receipt
    0.54
     subsistence
    0.52
     priority
    0.50
     capacity
    0.49
     sequencer
    0.49
     recipe
    0.48
     mandatory
    0.48
     questionnaire
    0.48
     distrust
    0.48
     breadth
    0.48
    POSITIVE LOGITS
    anın
    0.50
    IM
    0.49
    im
    0.48
    Editors
    0.47
    ddar
    0.47
    िक्की
    0.47
     प्रदूषण
    0.46
    devil
    0.46
    iyas
    0.46
    рін
    0.46
    Act Density 0.000%

    No Known Activations