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

    Neuronpedia

    INDEX
    Explanations

    rolling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     放
    -0.08
     bestimmen
    -0.08
     beobachten
    -0.08
     çağ
    -0.08
     frontière
    -0.08
    ickou
    -0.08
     महस
    -0.08
    402
    -0.08
    _mapping
    -0.07
     מתאים
    -0.07
    POSITIVE LOGITS
     gradual
    0.11
     gradually
    0.11
     gracefully
    0.10
    升级
    0.10
     upgrade
    0.10
     stagger
    0.10
     upgrades
    0.10
     обнов
    0.10
    upgrade
    0.09
     постепенно
    0.09
    Act Density 0.003%

    No Known Activations