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

    Neuronpedia

    INDEX
    Explanations

    use the explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Disabilities
    0.44
     Fan
    0.41
    erView
    0.41
     исходя
    0.40
     ligands
    0.40
     бетон
    0.39
     речо
    0.39
     Oils
    0.39
    fans
    0.38
    砌
    0.38
    POSITIVE LOGITS
     two
    0.60
     three
    0.57
     zwei
    0.53
     equation
    0.49
    两个
    0.49
     duas
    0.48
     deux
    0.47
     nuestra
    0.47
     persamaan
    0.46
     equations
    0.46
    Act Density 0.007%

    No Known Activations