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

    Neuronpedia

    INDEX
    Explanations

    function assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    carbonyl
    2.60
     setTimeout
    2.59
     disadvantaged
    2.50
    glm
    2.48
    ग्विजय
    2.46
     luar
    2.34
    ্পনিক
    2.33
     furnish
    2.26
    思います
    2.22
    मेड
    2.21
    POSITIVE LOGITS
    iors
    2.90
    ه
    2.55
    edly
    2.47
    l
    2.43
    ive
    2.41
    on
    2.37
    am
    2.35
    False
    2.31
    aient
    2.31
    iş
    2.28
    Act Density 0.015%

    No Known Activations