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

    Neuronpedia

    INDEX
    Explanations

    Code, questions, and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     여러
    -0.06
    orde
    -0.05
    หลด
    -0.05
     Sự
    -0.05
    _BUILD
    -0.05
     vorhand
    -0.05
     Resistance
    -0.05
    、本
    -0.05
    ición
    -0.05
     Voices
    -0.05
    POSITIVE LOGITS
     dart
    0.08
     next
    0.07
     tun
    0.07
     Oriental
    0.07
     tunnel
    0.07
     flashlight
    0.06
    /font
    0.06
    Bluetooth
    0.06
     Istanbul
    0.06
     }},↵
    0.06
    Act Density 0.001%

    No Known Activations