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

    Neuronpedia

    INDEX
    Explanations

    SQL `FROM` clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Similarly
    0.48
     However
    0.43
     although
    0.41
     Eff
    0.41
     on
    0.40
     In
    0.40
    0.40
     Although
    0.39
     similarly
    0.39
     Conversely
    0.39
    POSITIVE LOGITS
     descubre
    0.47
    全新的
    0.46
     nowe
    0.45
    تبار
    0.45
    最新的
    0.45
     temos
    0.44
    !”,
    0.44
     novi
    0.43
     العديد
    0.43
     descubrir
    0.42
    Act Density 0.000%

    No Known Activations