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

    Neuronpedia

    INDEX
    Explanations

    sports terminology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ѕ
    0.57
    鉆
    0.47
    Ĭ
    0.43
     ਸਿੰ
    0.41
    密封
    0.41
    ଢ
    0.41
    मूलन
    0.41
     एडवा
    0.40
    Tienes
    0.40
     домаћин
    0.40
    POSITIVE LOGITS
     at
    0.51
     Jugend
    0.46
     Markt
    0.46
     hangout
    0.44
     Edit
    0.44
     about
    0.44
     Pablo
    0.43
     Edited
    0.43
     p
    0.43
     New
    0.42
    Act Density 0.014%

    No Known Activations