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

    Neuronpedia

    INDEX
    Explanations

    values and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vésicules
    0.53
     wcout
    0.52
    𒅴
    0.52
    رک
    0.51
    blocking
    0.50
     Elovl
    0.50
     итальян
    0.50
    рет
    0.49
    erebbe
    0.49
    greedy
    0.49
    POSITIVE LOGITS
    :
    0.54
    S
    0.53
    '
    0.53
    Hamburger
    0.52
    Value
    0.52
    B
    0.51
     *
    0.50
    Type
    0.50
    Manager
    0.50
    H
    0.50
    Act Density 0.001%

    No Known Activations