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

    Neuronpedia

    INDEX
    Explanations

    š

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    š
    -1.10
    Š
    -0.82
    ш
    -0.61
    še
    -0.56
     š
    -0.54
    scaron
    -0.52
    ška
    -0.51
     Š
    -0.51
    SafeMath
    -0.51
    ş
    -0.49
    POSITIVE LOGITS
    eb
    0.64
    ei
    0.63
    ep
    0.63
    ema
    0.58
    eli
    0.58
    ede
    0.57
    eq
    0.57
    eo
    0.56
    ee
    0.56
     Efq
    0.56
    Act Density 0.020%

    No Known Activations