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

    Neuronpedia

    INDEX
    Explanations

    skip or continue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     omit
    0.59
     omission
    0.55
     omitted
    0.50
     sneaking
    0.47
     Om
    0.44
     অনুপস্থিত
    0.44
     skipped
    0.42
     withheld
    0.42
     chois
    0.40
    उच्च
    0.40
    POSITIVE LOGITS
     negativity
    0.44
    σκ
    0.40
    སྐ
    0.40
     అతి
    0.39
     instrumentation
    0.38
    设备的
    0.38
    нє
    0.38
    સ્ક
    0.38
    😼
    0.38
    negative
    0.38
    Act Density 0.001%

    No Known Activations