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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sprites
    0.41
     organelles
    0.39
     masukkan
    0.39
     aberrations
    0.39
     oscillators
    0.38
     operands
    0.38
    BSData
    0.37
     bitmaps
    0.37
     hashes
    0.37
     vortices
    0.37
    POSITIVE LOGITS
    ↵↵
    0.79
    ↵
    0.64
    ↵↵↵
    0.54
    ↵↵↵↵
    0.47
     However
    0.47
    ">
    0.45
    >
    0.45
    ↵↵↵↵↵
    0.45
    <h3>
    0.44
     Also
    0.44
    Act Density 1.973%

    No Known Activations