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

    Neuronpedia

    INDEX
    Explanations

    API endpoints and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    এই
    0.38
    蘿
    0.38
    IDAD
    0.37
    ถูก
    0.36
     সমাপ্ত
    0.36
    െന്ന
    0.36
    Evalu
    0.36
    ంటూ
    0.35
     đây
    0.35
    xcodep
    0.34
    POSITIVE LOGITS
     /
    0.59
     "/
    0.52
     /.
    0.50
    _/
    0.50
    =/
    0.47
     /ˈ
    0.47
     ./
    0.45
     /{
    0.45
    /
    0.45
     /(
    0.45
    Act Density 0.002%

    No Known Activations