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

    Neuronpedia

    INDEX
    Explanations

    dates of absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रिली
    0.41
    Meat
    0.40
     остав
    0.39
    分からない
    0.39
     नाच
    0.39
     ulteriori
    0.38
     интересу
    0.38
    亓
    0.38
    LETE
    0.37
     Lanes
    0.37
    POSITIVE LOGITS
     likewise
    0.46
     plaster
    0.40
    joins
    0.40
    Likewise
    0.39
     instinctively
    0.39
     económica
    0.37
     implied
    0.37
    HttpStatus
    0.37
    phal
    0.37
    ாள
    0.36
    Act Density 0.000%

    No Known Activations