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

    Neuronpedia

    INDEX
    Explanations

    to a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↼
    0.38
    ̧
    0.37
    UH
    0.37
     réfl
    0.37
     complètement
    0.36
    parametrize
    0.36
    kka
    0.35
    乘
    0.35
    ArrayBox
    0.35
    MovieModal
    0.34
    POSITIVE LOGITS
    <h3>
    0.50
    <blockquote>
    0.48
     suitable
    0.46
     Suitable
    0.41
     gc
    0.41
    Источник
    0.41
     nc
    0.40
     less
    0.39
     Nc
    0.39
     luke
    0.39
    Act Density 0.000%

    No Known Activations