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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Financial
    0.38
     Crunchy
    0.35
     Patreon
    0.34
    Xamarin
    0.34
    Oath
    0.34
     Financial
    0.34
    อะไร
    0.33
    Olivia
    0.33
    翀
    0.33
    Verse
    0.33
    POSITIVE LOGITS
     glycos
    0.38
    ೫
    0.37
    pubescens
    0.34
     robbers
    0.34
     삼
    0.32
     shortcomings
    0.32
    ̀
    0.32
    <0xA6>
    0.31
     handicrafts
    0.31
     shortcoming
    0.31
    Act Density 0.003%

    No Known Activations