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

    Neuronpedia

    INDEX
    Explanations

    pull request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ناخد
    0.42
    ovenants
    0.42
     قرارد
    0.42
     خدنا
    0.40
    濰
    0.40
    MOVEMENT
    0.38
     Беларусь
    0.38
    chore
    0.38
    一層
    0.37
    चन
    0.37
    POSITIVE LOGITS
     opened
    0.54
     critiques
    0.51
     Fork
    0.50
     critique
    0.49
     propose
    0.47
     reviewers
    0.47
     fork
    0.46
     reviews
    0.46
    Urls
    0.46
     পর্যালোচনা
    0.46
    Act Density 0.003%

    No Known Activations