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

    Neuronpedia

    INDEX
    Explanations

    cidr block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ęć
    0.40
     anek
    0.39
     পয়
    0.38
     pokaż
    0.38
    ියාව
    0.37
    markt
    0.37
     alken
    0.36
     पावसा
    0.36
     ውሃ
    0.36
     برف
    0.36
    POSITIVE LOGITS
     Least
    0.39
     LID
    0.37
     CID
    0.37
    output
    0.36
    CID
    0.36
     Output
    0.36
     Immediate
    0.35
     Unsupported
    0.35
     Fourth
    0.35
     फो
    0.35
    Act Density 0.000%

    No Known Activations