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

    Neuronpedia

    INDEX
    Explanations

    something wild

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    めっちゃ
    1.07
    !!)
    1.01
     tzv
    1.00
    !).
    0.96
     tzw
    0.96
     bzw
    0.96
    )!
    0.91
    !!!
    0.90
    !),
    0.89
    !!
    0.88
    POSITIVE LOGITS
     fucking
    0.75
     unbear
    0.74
     imposs
    0.74
     suffoc
    0.74
     irrevoc
    0.71
     seventeen
    0.70
     unbearable
    0.70
     hadn
    0.70
     eighteen
    0.70
     damned
    0.68
    Act Density 1.156%

    No Known Activations