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

    Neuronpedia

    INDEX
    Explanations

    finding or trying to get information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seaside
    0.45
     Writing
    0.45
     Talk
    0.44
     People
    0.42
    性の
    0.42
     on
    0.41
     writing
    0.40
     Write
    0.40
     gel
    0.40
    ুৎ
    0.40
    POSITIVE LOGITS
     jednotliv
    0.43
     мир
    0.42
     ర
    0.41
     menger
    0.41
    ienced
    0.41
     допо
    0.40
     DEPENDENCIA
    0.40
     Deter
    0.40
     आणखी
    0.40
     Rien
    0.40
    Act Density 0.006%

    No Known Activations