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

    Neuronpedia

    INDEX
    Explanations

    tasks requiring, objects that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ®.
    1.27
    ,--
    1.19
    .
    1.18
    。
    1.17
    ™.
    1.15
    €.
    1.08
    ।
    1.08
    ,—
    1.07
    ։
    1.07
    。.
    1.05
    POSITIVE LOGITS
     where
    0.88
     whose
    0.88
     deemed
    0.88
     jossa
    0.88
     requiring
    0.84
     resembling
    0.84
     which
    0.79
     joka
    0.79
     exhibiting
    0.75
     considered
    0.75
    Act Density 0.532%

    No Known Activations