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

    Neuronpedia

    INDEX
    Explanations

    diverse list of factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prolog
    0.47
     descoper
    0.40
     Alat
    0.39
    mesini
    0.39
     откри
    0.39
    發現
    0.38
     publiés
    0.38
    輌
    0.38
    ㈤
    0.38
    POSITORY
    0.38
    POSITIVE LOGITS
    摇头
    0.45
    Shake
    0.41
    shake
    0.40
    ENCI
    0.40
     eyebrow
    0.39
     observer
    0.39
     ind
    0.38
     observers
    0.38
     shaken
    0.38
    恵
    0.37
    Act Density 0.001%

    No Known Activations