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

    Neuronpedia

    INDEX
    Explanations

    actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intéress
    0.41
    стую
    0.41
    ictionary
    0.41
     interested
    0.40
    ason
    0.39
    old
    0.39
    жли
    0.38
    нибудь
    0.38
    Promise
    0.38
    ጠና
    0.38
    POSITIVE LOGITS
    \,.
    0.43
    abhav
    0.42
     প্রের
    0.41
    |=|
    0.41
    рования
    0.39
     Governo
    0.39
    ֩
    0.39
     фоне
    0.39
    VERNMENT
    0.38
     diphenyl
    0.38
    Act Density 0.001%

    No Known Activations