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

    Neuronpedia

    INDEX
    Explanations

    CPU, shape, Privacy, Roof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erythro
    0.54
    収納
    0.52
     epithelial
    0.47
    かれた
    0.46
    ILL
    0.46
     endothelial
    0.45
     sucrose
    0.44
     unto
    0.44
     caramelized
    0.43
     gravid
    0.43
    POSITIVE LOGITS
     Quadr
    0.50
    莅
    0.49
     Deep
    0.48
    ione
    0.47
     Quad
    0.47
    Quad
    0.46
    do
    0.45
    repr
    0.44
     Discount
    0.44
     Від
    0.44
    Act Density 0.005%

    No Known Activations