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

    Neuronpedia

    INDEX
    Explanations

    primarily, sections, portion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ву
    0.40
     హీ
    0.38
    COLOR
    0.38
     प्रमाण
    0.37
    Hình
    0.37
    Ter
    0.37
    LET
    0.36
     thấp
    0.36
    Calif
    0.36
    DLLEXPORT
    0.36
    POSITIVE LOGITS
    isme
    0.45
    imte
    0.40
     priorit
    0.39
     জানিয়ে
    0.38
     principled
    0.37
    </strong>
    0.37
    etse
    0.37
    itores
    0.36
    ）【
    0.36
    istent
    0.36
    Act Density 0.005%

    No Known Activations