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

    Neuronpedia

    INDEX
    Explanations

    press releases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ুনিক
    0.79
    माने
    0.67
     proposent
    0.64
    顶级
    0.63
     empfehlen
    0.62
    筁
    0.62
    orithms
    0.62
     inde
    0.61
     workable
    0.61
    कलन
    0.59
    POSITIVE LOGITS
     press
    3.59
     Press
    3.18
    Press
    3.07
    press
    2.98
     PRESS
    2.65
     प्रेस
    2.63
     пресс
    2.62
    PRESS
    2.48
     presse
    2.48
    プレス
    2.44
    Act Density 0.153%

    No Known Activations