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

    Neuronpedia

    INDEX
    Explanations

    advantageous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opravdu
    -1.33
    rätt
    -1.24
     oeil
    -1.20
    ⁈
    -1.17
    Mucha
    -1.16
     itinéraire
    -1.16
     déclaration
    -1.16
    corbic
    -1.11
     intest
    -1.10
     syk
    -1.10
    POSITIVE LOGITS
     
    1.22
    分かります
    1.19
    atized
    1.18
    Gonzalez
    1.16
     pequena
    1.15
    atique
    1.13
     $
    1.11
    ఱ
    1.10
    ii
    1.09
     ซึ่ง
    1.09
    Act Density 0.037%

    No Known Activations