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

    Neuronpedia

    INDEX
    Explanations

    standard procedures or formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.73
    1.39
    1
    1.32
    6
    1.31
    </h2>
    1.27
    9
    1.24
    ,
    1.10
    อน
    1.07
    3
    1.07
    у
    1.06
    POSITIVE LOGITS
     for
    1.48
    ۰
    1.35
    <0x80>
    1.30
    ine
    1.30
     For
    1.19
    ０
    1.18
    ach
    1.16
    it
    1.11
    ރު
    1.09
    rī
    1.09
    Act Density 0.026%

    No Known Activations