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

    Neuronpedia

    INDEX
    Explanations

    types of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    样子
    0.42
     '.</
    0.42
     idea
    0.40
    樣子
    0.39
     Empires
    0.39
     legendary
    0.38
     einem
    0.38
     verschiedenen
    0.38
    itesi
    0.38
     kısm
    0.38
    POSITIVE LOGITS
     kelamin
    0.62
     existentes
    0.48
    类型的
    0.41
     أنواع
    0.38
    aches
    0.37
     biases
    0.36
     discrimin
    0.35
     licences
    0.34
    種類の
    0.34
    welling
    0.34
    Act Density 0.025%

    No Known Activations