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

    Neuronpedia

    INDEX
    Explanations

    words following common terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     with
    0.41
    at
    0.37
    ka
    0.37
     boar
    0.36
     Pong
    0.36
     only
    0.35
     esters
    0.35
    াস
    0.34
     métal
    0.34
     mon
    0.34
    POSITIVE LOGITS
    اج
    0.40
     Сим
    0.40
     मेगा
    0.37
     परिस्थिति
    0.37
     рекомен
    0.37
    возможно
    0.37
    ذ
    0.36
     своём
    0.35
    ३
    0.35
    <unused75>
    0.35
    Act Density 0.011%

    No Known Activations