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

    Neuronpedia

    INDEX
    Explanations

    It wasn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skater
    0.48
     distributes
    0.48
     hydrophobic
    0.46
     probationary
    0.46
     leaderboard
    0.45
     buckle
    0.45
     learns
    0.45
     waterslide
    0.45
     veggie
    0.44
     plug
    0.44
    POSITIVE LOGITS
     Erkennt
    0.44
     بشأن
    0.43
    گذ
    0.43
     început
    0.43
    حضرت
    0.42
     زیب
    0.41
    Τ
    0.41
     Di
    0.41
    Di
    0.40
    yuk
    0.40
    Act Density 0.036%

    No Known Activations