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

    Neuronpedia

    INDEX
    Explanations

    aj

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     özgür
    -0.07
     Dirt
    -0.07
    ンプ
    -0.07
     bền
    -0.07
     ön
    -0.07
    €™
    -0.07
     ø
    -0.07
     Cinder
    -0.07
    €™
    -0.07
    .onDestroy
    -0.07
    POSITIVE LOGITS
    ag
    0.13
    ac
    0.13
    ak
    0.12
    AG
    0.12
    am
    0.12
    ad
    0.11
    ai
    0.11
    AI
    0.11
    AK
    0.11
    au
    0.11
    Act Density 1.326%

    No Known Activations