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

    Neuronpedia

    INDEX
    Explanations

    ver**b** endings like **ido** **ir** **iendo**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     থাকুন
    0.52
     থাকবেন
    0.50
    藠
    0.50
     diastere
    0.49
    ńskiego
    0.49
    amerikanischer
    0.48
     ہوگی
    0.47
     झालं
    0.47
     precluded
    0.47
    ዐይን
    0.46
    POSITIVE LOGITS
    ido
    1.12
    ir
    1.09
    idores
    1.03
    irse
    0.98
    iendo
    0.96
    ible
    0.94
    imos
    0.91
    imento
    0.91
    idora
    0.91
    IR
    0.90
    Act Density 0.032%

    No Known Activations