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

    Neuronpedia

    INDEX
    Explanations

    articulate a singular item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accessing
    0.46
     instantiation
    0.44
     allocating
    0.41
     sourcing
    0.41
     deploying
    0.40
     pagination
    0.39
     procrastination
    0.38
    箇所
    0.38
     applying
    0.38
     sometime
    0.38
    POSITIVE LOGITS
     marathon
    0.50
     toothbrush
    0.49
     multitude
    0.48
     ponytail
    0.48
     waterfall
    0.47
     spreadsheet
    0.47
     smile
    0.47
     microphone
    0.47
     handshake
    0.47
     mustache
    0.47
    Act Density 0.066%

    No Known Activations