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

    Neuronpedia

    INDEX
    Explanations

    breaking down information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㴦
    0.57
    วิธีการ
    0.53
    㚼
    0.52
    еш
    0.52
    愘
    0.52
    燮
    0.50
    Ⴀ
    0.50
    㶱
    0.50
    穸
    0.49
    ಯು
    0.48
    POSITIVE LOGITS
     proved
    0.49
    2
    0.46
    3
    0.45
     availed
    0.45
     trouser
    0.44
    IC
    0.44
     proves
    0.43
    "
    0.43
    dır
    0.42
     pune
    0.42
    Act Density 0.004%

    No Known Activations