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

    Neuronpedia

    INDEX
    Explanations

    controlled by parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Madison
    0.45
    價格
    0.42
    京
    0.40
    Бі
    0.39
    Lyon
    0.39
    Skin
    0.38
    ORN
    0.38
     前
    0.38
    Bur
    0.37
    Liverpool
    0.37
    POSITIVE LOGITS
    InitTypeDef
    0.44
     ආරක්ෂ
    0.44
    бычно
    0.42
     imaginative
    0.41
     보호
    0.40
    ிருப்பது
    0.40
     normally
    0.39
     ಸಾಮಾನ್ಯವಾಗಿ
    0.39
     isomeric
    0.39
     protected
    0.39
    Act Density 0.000%

    No Known Activations