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

    Neuronpedia

    INDEX
    Explanations

    quotes followed by t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     basso
    0.51
     von
    0.48
     pseudonym
    0.47
     estremamente
    0.46
     lccn
    0.44
     generale
    0.44
     anni
    0.44
     trademark
    0.44
     nonché
    0.43
     microorganism
    0.43
    POSITIVE LOGITS
    Из
    0.64
    Вы
    0.61
    Looks
    0.58
    Ре
    0.57
    //
    0.56
    Раз
    0.56
    Just
    0.53
    Pretty
    0.52
    Keeping
    0.50
    Start
    0.50
    Act Density 0.108%

    No Known Activations