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

    Neuronpedia

    INDEX
    Explanations

    temperature readings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %).
    0.40
    \%).
    0.37
    \%)
    0.37
    )$.
    0.35
    \%.
    0.35
    \%
    0.33
    \%),
    0.33
    )}.
    0.32
    /<
    0.31
    )].
    0.30
    POSITIVE LOGITS
    ısında
    0.36
     krishna
    0.35
     sebagian
    0.34
    dessä
    0.34
     ایسا
    0.33
     informée
    0.33
     পাকিস্তানী
    0.32
    हायला
    0.32
     మీడియా
    0.32
    ⏎
    0.32
    Act Density 0.011%

    No Known Activations