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

    Neuronpedia

    INDEX
    Explanations

    expert in the field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     könne
    0.83
     않아
    0.70
     abgest
    0.69
     pointA
    0.67
    的有
    0.66
    ודה
    0.65
    वर
    0.65
     способен
    0.65
    きた
    0.64
     salga
    0.64
    POSITIVE LOGITS
     कोरोनावायरस
    1.02
     eventful
    0.93
     hearsay
    0.80
     Characters
    0.80
    Characters
    0.79
    ँव
    0.76
     auss
    0.75
    पोरेशन
    0.75
     আবুল
    0.74
     Pp
    0.74
    Act Density 0.001%

    No Known Activations