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

    Neuronpedia

    INDEX
    Explanations

    Goa, Roof, Fairy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    corp
    0.38
    یین
    0.38
    丳
    0.38
    صار
    0.37
     چین
    0.36
     بی‌
    0.36
    ündet
    0.35
    ⠈
    0.35
     Hartmann
    0.35
     ميل
    0.35
    POSITIVE LOGITS
     गोवा
    0.43
     Goa
    0.43
     roof
    0.43
     Roof
    0.42
    roof
    0.42
    greencar
    0.42
     fairy
    0.42
    Roof
    0.42
    questa
    0.42
    씽
    0.41
    Act Density 0.000%

    No Known Activations