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

    Neuronpedia

    INDEX
    Explanations

    e followed by cd, clips, ins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bois
    0.45
    Piper
    0.44
    Three
    0.42
    Bailey
    0.42
    Two
    0.40
    Boy
    0.40
     Synd
    0.39
    utives
    0.38
    Seattle
    0.38
    мпа
    0.38
    POSITIVE LOGITS
     beef
    0.44
    ณี
    0.43
     නව
    0.43
     હંમે
    0.41
     élet
    0.41
    ellido
    0.39
    ufe
    0.39
     Кан
    0.39
     淡
    0.39
     wszel
    0.38
    Act Density 0.001%

    No Known Activations