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

    Neuronpedia

    INDEX
    Explanations

    creation from nothing or nowhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রতিবেদন
    0.38
     LITTLE
    0.37
    ্ধে
    0.37
    鄙
    0.37
     Unlock
    0.36
    大部分
    0.35
    ീ
    0.35
    ುತ್ತ
    0.34
     ports
    0.34
    little
    0.34
    POSITIVE LOGITS
     nowhere
    1.24
     Nowhere
    1.01
     nulle
    0.83
     thin
    0.80
    Thin
    0.74
     Thin
    0.70
    nullptr
    0.70
    thin
    0.70
     void
    0.68
     inexist
    0.66
    Act Density 0.019%

    No Known Activations