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

    Neuronpedia

    INDEX
    Explanations

    OnlyFans content and accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     countertop
    0.39
     bonsai
    0.38
     unmistakable
    0.38
     dział
    0.38
     intu
    0.38
     oxidizing
    0.37
    🍢
    0.37
     acetone
    0.37
     unmist
    0.37
     giocatore
    0.37
    POSITIVE LOGITS
     for
    0.55
    X
    0.55
    an
    0.52
    s
    0.50
    m
    0.47
    d
    0.46
    p
    0.46
    om
    0.46
    ay
    0.45
    a
    0.43
    Act Density 0.001%

    No Known Activations