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

    Neuronpedia

    INDEX
    Explanations

    VRAM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    foundland
    0.35
     rhubarb
    0.31
     ाट
    0.30
    trashItem
    0.29
    calup
    0.29
     erythe
    0.29
     peony
    0.29
    bottlecap
    0.28
    loaf
    0.28
    echolog
    0.28
    POSITIVE LOGITS
    М
    0.38
    aaS
    0.38
     D
    0.36
     B
    0.35
    AT
    0.34
    А
    0.34
    Q
    0.34
    IDs
    0.33
     T
    0.33
    Р
    0.33
    Act Density 0.066%

    No Known Activations