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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.85
    '
    0.71
    ’
    0.58
    :
    0.56
    ти
    0.52
    l
    0.49
    ot
    0.49
    ని
    0.47
    ationale
    0.46
    -”
    0.45
    POSITIVE LOGITS
     with
    0.84
     for
    0.72
    。)
    0.66
     on
    0.63
    ங்கிணை
    0.62
     invigor
    0.61
     tendencias
    0.60
     последствия
    0.59
     presion
    0.58
     digraph
    0.58
    Act Density 0.003%

    No Known Activations