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

    Neuronpedia

    INDEX
    Explanations

    parts of names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    brite
    0.49
     antennis
    0.48
     отде
    0.47
    ᱘
    0.46
     relaciona
    0.45
     otras
    0.45
     ଏ
    0.45
     κά
    0.44
     externes
    0.44
     organizações
    0.44
    POSITIVE LOGITS
    ווי
    0.45
    magic
    0.43
    목
    0.43
    德
    0.42
    ิน
    0.41
    </strong>
    0.40
     permainan
    0.40
    cutter
    0.40
     svom
    0.39
    忘
    0.39
    Act Density 0.001%

    No Known Activations