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

    Neuronpedia

    INDEX
    Explanations

    steps, lists, cross

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insol
    0.45
    INSON
    0.44
    unal
    0.44
    irat
    0.43
    oir
    0.43
    inson
    0.43
    oll
    0.43
     och
    0.43
    ankar
    0.43
     निधन
    0.42
    POSITIVE LOGITS
    향
    0.50
    ート
    0.45
    愛
    0.43
    शै
    0.42
     đọc
    0.41
    レー
    0.40
    しゃ
    0.40
     wirelessly
    0.40
     Less
    0.40
    ಂಗ್ರೆ
    0.40
    Act Density 0.008%

    No Known Activations