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

    Neuronpedia

    INDEX
    Explanations

    list items or formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zeka
    0.39
    ೦
    0.39
    Programming
    0.39
     об
    0.38
     debts
    0.38
    Properties
    0.38
     PROPERTIES
    0.38
     Clinton
    0.37
     対応
    0.37
    fahrer
    0.37
    POSITIVE LOGITS
    昦
    0.38
     بهتر
    0.38
    ร์
    0.37
    ะนั้น
    0.36
    最終
    0.35
    ervlak
    0.35
    lished
    0.35
    अमेर
    0.34
     Aks
    0.34
    विधा
    0.34
    Act Density 0.010%

    No Known Activations