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

    Neuronpedia

    INDEX
    Explanations

    closing tags or delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essentials
    0.63
     reasons
    0.57
    /
    0.54
     abe
    0.53
    \_
    0.53
     photos
    0.52
     str
    0.48
     plenty
    0.48
    তন্ত্র
    0.47
    ical
    0.47
    POSITIVE LOGITS
    >,
    1.38
    >.
    1.31
    >)
    1.24
    >),
    1.20
    >;
    1.19
    >[
    1.18
    >"
    1.12
    >]
    1.12
    >'
    1.10
    >
    1.09
    Act Density 0.001%

    No Known Activations