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

    Neuronpedia

    INDEX
    Explanations

    incidental or overpowering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rifugal
    0.47
     muffled
    0.46
     breeding
    0.45
    levance
    0.44
    剡
    0.44
     mascot
    0.44
     elegans
    0.42
     soaked
    0.42
     Jahrze
    0.42
     specimen
    0.41
    POSITIVE LOGITS
     алге
    0.48
    Y
    0.45
    Obama
    0.43
    тету
    0.40
    비
    0.40
     przyj
    0.39
     byť
    0.39
    โทร
    0.39
     нару
    0.38
    현
    0.38
    Act Density 0.001%

    No Known Activations