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

    Neuronpedia

    INDEX
    Explanations

    Error or technical settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    в
    2.46
    an
    2.36
    가
    2.30
    ли
    2.30
    ان
    2.16
    ać
    2.10
     heed
    2.09
    ر
    1.98
    一来
    1.98
    𝐵
    1.97
    POSITIVE LOGITS
    tion
    2.63
     lineColorSpace
    2.58
    ted
    2.50
    ير
    2.41
    tor
    2.38
    2.27
    tio
    2.22
    اً
    2.21
    tad
    2.18
    tk
    2.18
    Act Density 0.187%

    No Known Activations