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

    Neuronpedia

    INDEX
    Explanations

    tennis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ič
    2.05
    ન
    1.79
    iče
    1.75
    ó
    1.73
    iya
    1.71
    но
    1.66
    дің
    1.66
    ために
    1.66
    いますが
    1.63
    दर्शक
    1.62
    POSITIVE LOGITS
    ς
    1.87
    Arial
    1.77
     remit
    1.58
    ่
    1.56
    LER
    1.55
    り
    1.55
    اونلو
    1.55
     disregard
    1.53
    एस
    1.52
    GES
    1.52
    Act Density 0.001%

    No Known Activations