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

    Neuronpedia

    INDEX
    Explanations

    anonymous sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CEO
    0.44
     video
    0.44
     recorded
    0.43
     Ms
    0.41
     texted
    0.41
     tweeted
    0.41
     Reported
    0.41
     Başkanı
    0.41
     publicized
    0.41
     Chief
    0.40
    POSITIVE LOGITS
    Anonymous
    0.53
    anonymous
    0.45
    스티
    0.45
     insiders
    0.44
    contributors
    0.43
     промышленности
    0.42
     የሚያ
    0.41
    uno
    0.40
     confid
    0.40
     EAS
    0.40
    Act Density 0.006%

    No Known Activations