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

    Neuronpedia

    INDEX
    Explanations

    safe and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ки
    0.42
     scoop
    0.41
     Kies
    0.41
    kij
    0.38
     Kelley
    0.37
     المك
    0.37
    キン
    0.37
     mâ
    0.36
     scoops
    0.36
     sco
    0.36
    POSITIVE LOGITS
     formally
    0.33
    ष्मान
    0.32
    šić
    0.31
     JORDAN
    0.31
     அமைச்ச
    0.31
     એટલે
    0.31
    Sp
    0.31
     राजवंश
    0.31
    andered
    0.30
    optosis
    0.30
    Act Density 0.016%

    No Known Activations