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

    Neuronpedia

    INDEX
    Explanations

    New York Times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aver
    0.60
     ony
    0.55
     p
    0.55
     sider
    0.55
    PROVIDED
    0.54
    を使用した
    0.54
    oughs
    0.53
     don
    0.53
     hä
    0.53
    issimi
    0.53
    POSITIVE LOGITS
    relsen
    0.69
    elab
    0.68
    javase
    0.68
    лія
    0.67
    łe
    0.67
    ił
    0.66
    shoz
    0.65
    rivere
    0.62
    ელ
    0.62
     рә
    0.62
    Act Density 0.000%

    No Known Activations