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

    Neuronpedia

    INDEX
    Explanations

    at which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SimSun
    0.50
    倬
    0.46
     the
    0.46
    Hua
    0.45
     Tuscany
    0.44
     Pepper
    0.40
     gabb
    0.40
    ٢
    0.40
    蝠
    0.40
    栀
    0.40
    POSITIVE LOGITS
     whereby
    0.46
    inflation
    0.46
    <unused54>
    0.44
     auquel
    0.41
    穩定
    0.40
     achieved
    0.40
     rewarded
    0.40
     RATE
    0.40
    accepted
    0.39
    impact
    0.39
    Act Density 0.003%

    No Known Activations