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

    Neuronpedia

    INDEX
    Explanations

    explanation or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.51
    l
    0.49
    h
    0.46
    p
    0.44
    ه
    0.44
              
    0.41
    m
    0.40
    <0x0D>
    0.40
    b
    0.39
    ));
    0.39
    POSITIVE LOGITS
     bahwa
    0.66
     rằng
    0.55
     bahawa
    0.54
     kwamba
    0.52
     that
    0.52
     ότι
    0.51
     दैट
    0.49
     että
    0.44
     أنه
    0.44
    ว่า
    0.43
    Act Density 0.020%

    No Known Activations