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

    Neuronpedia

    INDEX
    Explanations

    Explaining or paraphrasing text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    יל
    -0.08
     kat
    -0.08
     beams
    -0.08
    صب
    -0.07
     Boy
    -0.07
     Independence
    -0.07
     Kat
    -0.07
    .kt
    -0.07
     mọ
    -0.07
     bevestigd
    -0.07
    POSITIVE LOGITS
     understandable
    0.10
    interpret
    0.10
     Tradu
    0.10
     traduction
    0.09
     содержание
    0.09
     traduit
    0.09
     interpr
    0.09
     traduc
    0.09
    Interpret
    0.09
     предназнач
    0.08
    Act Density 0.024%

    No Known Activations