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

    Neuronpedia

    INDEX
    Explanations

    POST http request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MaxPool
    0.40
    多分
    0.39
    证明
    0.39
    દેશ
    0.38
     improbable
    0.38
    ﾙ
    0.37
     unlikely
    0.37
    amorph
    0.36
     धरा
    0.36
     Ronaldo
    0.35
    POSITIVE LOGITS
     akses
    0.44
     access
    0.44
     repaso
    0.43
     Ú
    0.42
     Being
    0.41
     trasero
    0.41
    Being
    0.41
     depan
    0.40
     being
    0.40
     एक्सेस
    0.40
    Act Density 0.000%

    No Known Activations