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

    Neuronpedia

    INDEX
    Explanations

    data structures and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     belirl
    0.53
    PathDirectory
    0.49
    Nueva
    0.49
    Año
    0.48
    Francesco
    0.48
    ၺ
    0.48
    манов
    0.47
     Inicio
    0.47
    Giovanni
    0.46
     petits
    0.46
    POSITIVE LOGITS
     سيكون
    0.46
    現代
    0.45
    విధ
    0.45
    纹
    0.44
    šću
    0.44
    ଙ୍କ
    0.43
    㧿
    0.42
     thẩm
    0.42
     يش
    0.41
    aise
    0.41
    Act Density 0.000%

    No Known Activations