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

    Neuronpedia

    INDEX
    Explanations

    text HELP HOME

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    📡
    0.67
     aires
    0.64
     الموسم
    0.64
     axiomatic
    0.63
     juxt
    0.62
    🚀
    0.62
    ہم
    0.61
    🏌
    0.61
    تها
    0.60
    ..!
    0.60
    POSITIVE LOGITS
    IN
    0.70
     отправ
    0.66
    ag
    0.65
     Envoy
    0.64
    I
    0.64
    q
    0.64
    ="{
    0.63
     Troops
    0.63
     Troop
    0.63
     Escape
    0.63
    Act Density 0.001%

    No Known Activations