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

    Neuronpedia

    INDEX
    Explanations

    Human Feedback

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     поне
    0.40
    Chk
    0.38
    allaitement
    0.38
    ૪
    0.37
     சக
    0.37
     ಸ್ವಾ
    0.36
    㝡
    0.36
     ფუნქ
    0.36
    介
    0.36
    踊
    0.35
    POSITIVE LOGITS
     Parameter
    0.46
     Endpoint
    0.42
    parameter
    0.41
    Parameter
    0.41
     Product
    0.39
     Trop
    0.39
    Endpoint
    0.38
     Starting
    0.38
     ad
    0.38
     Contact
    0.37
    Act Density 0.003%

    No Known Activations