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

    Neuronpedia

    INDEX
    Explanations

    risks of negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    txt
    0.53
    room
    0.52
    し
    0.51
    ’
    0.50
    ς
    0.49
    the
    0.48
    রাও
    0.48
    ровать
    0.48
    так
    0.47
    ured
    0.47
    POSITIVE LOGITS
    on
    0.71
     unei
    0.57
     unui
    0.56
     utilizó
    0.54
     recour
    0.53
    ES
    0.52
     UBND
    0.52
     încep
    0.52
    /")
    0.52
    một
    0.52
    Act Density 0.283%

    No Known Activations