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

    Neuronpedia

    INDEX
    Explanations

    Actions involving people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     其
    -0.07
    ді
    -0.07
     bakeka
    -0.06
     внутр
    -0.06
    923
    -0.06
    าชน
    -0.06
    มหานคร
    -0.06
     dört
    -0.06
    ━
    -0.06
    }*/↵↵
    -0.06
    POSITIVE LOGITS
    _event
    0.07
     Coy
    0.07
     rubbed
    0.07
     tapped
    0.07
     Ago
    0.06
     verwendet
    0.06
    _counts
    0.06
    DidAppear
    0.06
     tapping
    0.06
     [...
    0.06
    Act Density 0.080%

    No Known Activations