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

    Neuronpedia

    INDEX
    Explanations

    hypothetical scenarios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etype
    -0.08
    Voltage
    -0.08
     Puis
    -0.07
     regrets
    -0.07
     fan
    -0.07
    atetime
    -0.07
    摘要
    -0.07
    iate
    -0.07
     особенности
    -0.07
     elekt
    -0.07
    POSITIVE LOGITS
     Scenario
    0.09
     Instead
    0.09
    instead
    0.09
     Would
    0.09
     zouden
    0.09
     hätten
    0.09
    peria
    0.08
     instead
    0.08
     hypothetical
    0.08
     auraient
    0.08
    Act Density 0.039%

    No Known Activations