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

    Neuronpedia

    INDEX
    Explanations

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ப்பிர
    0.71
     خفیہ
    0.69
    긴
    0.63
     réel
    0.63
     おり
    0.63
    orgt
    0.62
    ającej
    0.62
     reali
    0.61
    পার
    0.61
    以内に
    0.61
    POSITIVE LOGITS
     example
    3.88
     Example
    3.54
     examples
    3.48
    Example
    3.48
    example
    3.42
     Examples
    3.32
     esempio
    3.24
     exemplo
    3.22
     ejemplo
    3.18
    Examples
    3.15
    Act Density 1.512%

    No Known Activations