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

    Neuronpedia

    INDEX
    Explanations

    numbers, code, and biblical verses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៤
    0.48
     جوړونکو
    0.48
    鿆
    0.47
    ４
    0.46
     चौथे
    0.45
    ᱔
    0.44
     fyra
    0.44
     čtyř
    0.44
     fourteen
    0.43
     zwölf
    0.43
    POSITIVE LOGITS
    5
    0.58
    8
    0.51
     source
    0.45
    0.39
    0.39
    ☆
    0.38
     Source
    0.38
     in
    0.38
     pe
    0.37
     video
    0.36
    Act Density 0.005%

    No Known Activations