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

    Neuronpedia

    INDEX
    Explanations

    code string values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    1.48
     “…
    1.20
     ‘
    1.20
     「
    1.19
     „
    1.18
     «
    1.15
     Clothing
    1.09
     Think
    1.07
     Mindfulness
    1.07
     “[
    1.06
    POSITIVE LOGITS
    '",
    1.14
    nombre
    1.11
    curvature
    1.09
    "));
    1.08
    hello
    1.08
    '))
    1.07
    "]').
    1.06
    **/
    1.05
    constants
    1.05
    "])
    1.05
    Act Density 0.286%

    No Known Activations