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

    Neuronpedia

    INDEX
    Explanations

    compound nouns and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лии
    0.42
     rakk
    0.40
     impoz
    0.40
     diarios
    0.39
     maksimal
    0.39
     hypergly
    0.38
    zov
    0.38
     antiguas
    0.38
    rafl
    0.38
    bble
    0.38
    POSITIVE LOGITS
     Resource
    0.43
     Including
    0.41
     Great
    0.40
     Dragon
    0.39
     Whom
    0.39
     Desert
    0.37
     Many
    0.37
     Ф
    0.37
     Cabin
    0.37
     Which
    0.36
    Act Density 0.000%

    No Known Activations