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

    Neuronpedia

    INDEX
    Explanations

    process, firewall, oxidized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Discussion
    0.44
     Lewis
    0.40
    ández
    0.40
    ''
    0.39
    rise
    0.38
     Montgomery
    0.38
     Materials
    0.38
    is
    0.38
    anesulfonyl
    0.37
     comentarios
    0.37
    POSITIVE LOGITS
    應用
    0.40
     краю
    0.39
     слой
    0.38
     идея
    0.37
     LAYER
    0.37
    槽
    0.36
    侎
    0.36
     ও
    0.36
    чка
    0.36
     oxidized
    0.36
    Act Density 0.000%

    No Known Activations