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

    Neuronpedia

    INDEX
    Explanations

    language and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oves
    0.43
    uken
    0.43
    ously
    0.42
    adeon
    0.42
    oris
    0.41
    ాడు
    0.41
    affin
    0.40
    zeigen
    0.40
    aser
    0.40
     Gewalt
    0.40
    POSITIVE LOGITS
    न
    0.52
     formación
    0.52
    ানিতে
    0.52
    ನ
    0.52
    más
    0.51
    기
    0.51
    嘗試
    0.50
    ྲ
    0.50
     possíveis
    0.49
    ን
    0.49
    Act Density 0.006%

    No Known Activations