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

    Neuronpedia

    INDEX
    Explanations

    letters followed by punctuation or slash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    okatokat
    0.35
    癃
    0.34
    HARAD
    0.33
     ɖ
    0.33
    ERICK
    0.33
    HOBBIT
    0.32
    OGRAF
    0.32
    REGIUNE
    0.32
     σημαν
    0.32
    avkhat
    0.32
    POSITIVE LOGITS
    that
    0.52
    i
    0.46
    max
    0.40
    if
    0.40
    we
    0.40
     D
    0.39
     that
    0.39
    0.39
    t
    0.38
    epsilon
    0.38
    Act Density 0.352%

    No Known Activations