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

    Neuronpedia

    INDEX
    Explanations

    investigate cause problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elto
    0.44
    networks
    0.43
    st
    0.42
    stitch
    0.41
    Imaging
    0.41
    minster
    0.41
    libro
    0.41
    detection
    0.40
    te
    0.40
     textiles
    0.40
    POSITIVE LOGITS
     muda
    0.54
     harmonica
    0.51
     dapat
    0.49
    (^
    0.48
    ک
    0.45
     veya
    0.45
    )
    0.45
     latar
    0.44
     ک
    0.44
     lembut
    0.43
    Act Density 0.001%

    No Known Activations