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

    Neuronpedia

    INDEX
    Explanations

    pronoun and common word sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     copyright
    0.38
    0.37
     reported
    0.35
    0
    0.35
    ↵
    0.34
     $
    0.34
     notable
    0.34
     and
    0.33
     notably
    0.32
     \\
    0.32
    POSITIVE LOGITS
    আপনি
    0.37
    你就
    0.37
     завжди
    0.37
     حتی
    0.36
     మనం
    0.35
     kabhi
    0.35
     навіть
    0.35
     당신
    0.35
     якого
    0.35
    那你
    0.35
    Act Density 0.000%

    No Known Activations