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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coefficient
    -0.07
     числі
    -0.07
     フ
    -0.07
    inp
    -0.07
    ための
    -0.06
    (tb
    -0.06
     stil
    -0.06
    군
    -0.06
     několika
    -0.06
     useContext
    -0.06
    POSITIVE LOGITS
     action
    0.07
    enterprise
    0.07
     Pins
    0.07
    .mapping
    0.06
     Asian
    0.06
     morally
    0.06
    Action
    0.06
    ...");↵
    0.06
    configured
    0.06
     joining
    0.06
    Act Density 0.001%

    No Known Activations