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

    Neuronpedia

    INDEX
    Explanations

    tinyurl and tamarind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ximo
    0.43
    ție
    0.43
    resi
    0.42
    órios
    0.42
     giovani
    0.42
    olina
    0.40
    ți
    0.39
    ération
    0.39
    rí
    0.38
    atii
    0.38
    POSITIVE LOGITS
    VRDR
    0.41
     Writing
    0.39
    ceff
    0.38
    кг
    0.37
    Writing
    0.37
    劲
    0.36
     writings
    0.36
    কথ
    0.36
    勁
    0.36
    Доб
    0.35
    Act Density 0.000%

    No Known Activations