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

    Neuronpedia

    INDEX
    Explanations

    warfare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cornwall
    -0.07
    Pointer
    -0.07
    Group
    -0.06
    厚
    -0.06
    _ADC
    -0.06
    727
    -0.06
    _consumer
    -0.06
    Employee
    -0.06
    師
    -0.06
    嘛
    -0.06
    POSITIVE LOGITS
    /NĐ
    0.07
     jasmine
    0.07
    παίδ
    0.06
     ⓘ
    0.06
     competitors
    0.06
     نحوه
    0.06
     İngilizce
    0.06
     hydration
    0.06
    tensorflow
    0.06
    iện
    0.06
    Act Density 0.015%

    No Known Activations