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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ARI
    -0.07
     Films
    -0.07
    tu
    -0.07
     intervene
    -0.07
     published
    -0.06
     Bands
    -0.06
    _actor
    -0.06
     namespaces
    -0.06
     forCell
    -0.06
    POSITIVE LOGITS
    πος
    0.06
     pornofil
    0.06
     xmax
    0.06
     дво
    0.06
     Origin
    0.06
     Сред
    0.06
    Verdana
    0.06
    m
    0.06
    �
    0.06
     mq
    0.06
    Act Density 0.002%

    No Known Activations