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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal strings with digits and letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prer
    0.29
     humane
    0.27
     cylinders
    0.27
     Kuchen
    0.27
     fish
    0.27
     Great
    0.26
     prog
    0.26
     room
    0.26
     engulfed
    0.26
     Maschine
    0.26
    POSITIVE LOGITS
    <unused105>
    0.37
    𝟮
    0.35
    <unused1147>
    0.33
     १६
    0.33
    <unused253>
    0.33
    <unused2040>
    0.32
    ทธิ
    0.32
    𝟯
    0.32
    ۱۲
    0.31
    ਲਾ
    0.31
    Act Density 0.014%

    No Known Activations