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

    Neuronpedia

    INDEX
    Explanations

    explanationscripts, and communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     în
    0.75
     in
    0.70
     new
    0.70
     ג
    0.66
    びっくり
    0.65
     with
    0.63
     at
    0.62
     במ
    0.62
     깜
    0.62
     preliminary
    0.61
    POSITIVE LOGITS
     혹은
    0.90
     yoki
    0.86
    หรือ
    0.83
     ataupun
    0.80
    もしくは
    0.80
     হোক
    0.76
     ಅಥವಾ
    0.76
     లేదా
    0.75
    或者
    0.73
     அல்லது
    0.72
    Act Density 0.017%

    No Known Activations