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

    Neuronpedia

    INDEX
    Explanations

    bolded instructions or notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <i>
    0.43
     கட்டப்பட்டது
    0.40
    ком
    0.38
    мые
    0.37
    গঠ
    0.36
     insectes
    0.36
    ྒྱ
    0.35
    任何人
    0.35
    굉장
    0.35
    ֥
    0.35
    POSITIVE LOGITS
    ing
    0.49
    logits
    0.45
     first
    0.44
    ist
    0.42
    is
    0.41
     numerator
    0.40
    see
    0.40
     మా
    0.40
     logits
    0.40
     likelihood
    0.39
    Act Density 0.001%

    No Known Activations