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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.57
    ون
    0.54
    at
    0.50
    ాన్ని
    0.50
    ే
    0.50
    י
    0.49
    ed
    0.47
    f
    0.46
    ي
    0.46
    ა
    0.45
    POSITIVE LOGITS
     to
    0.73
     that
    0.56
     it
    0.52
    ong
    0.48
    ulation
    0.43
    that
    0.43
     که
    0.41
    й
    0.41
     que
    0.41
    0.40
    Act Density 1.365%

    No Known Activations