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

    Neuronpedia

    INDEX
    Explanations

    explaining technical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seemingly
    1.13
     timely
    1.04
     był
    1.04
     privind
    1.03
     ViewHolder
    1.02
    ی
    1.00
    既
    1.00
     ensuring
    1.00
     była
    1.00
     concerning
    1.00
    POSITIVE LOGITS
    е
    1.33
    pawns
    1.32
    IZE
    1.24
    диа
    1.21
    또
    1.21
    OSED
    1.19
    ꯕ
    1.18
    σ
    1.18
    많
    1.17
    ان
    1.16
    Act Density 0.000%

    No Known Activations