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

    Neuronpedia

    INDEX
    Explanations

    are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是一个
    0.73
    altezza
    0.69
    是一個
    0.68
     ہے
    0.67
     a
    0.66
    𝗮
    0.64
    ється
    0.64
    是一款
    0.63
    nThe
    0.62
    ipitation
    0.61
    POSITIVE LOGITS
     vulnerabilities
    0.78
     notoriously
    0.70
    往往
    0.69
     vulnerable
    0.64
     нередко
    0.63
     undermined
    0.63
     often
    0.59
     unlikely
    0.59
     disadvant
    0.59
    시설
    0.58
    Act Density 0.003%

    No Known Activations