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

    Neuronpedia

    INDEX
    Explanations

    performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کہ
    0.42
     중간
    0.40
     intervening
    0.40
    вість
    0.40
     sanct
    0.40
     cư
    0.38
    stdin
    0.37
     ciekaw
    0.35
     групп
    0.33
     interessant
    0.33
    POSITIVE LOGITS
     vậy
    0.49
     ainsi
    0.45
     así
    0.41
     additionally
    0.40
     Inclusive
    0.40
     with
    0.40
    olulu
    0.39
     Measurement
    0.39
     Inclusion
    0.38
     bè
    0.38
    Act Density 0.000%

    No Known Activations