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

    Neuronpedia

    INDEX
    Explanations

    Technical device descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Conclusion
    -0.07
     twe
    -0.07
    Proof
    -0.07
     amplifier
    -0.06
    	top
    -0.06
     term
    -0.06
     remedies
    -0.06
     Coronavirus
    -0.06
     protagonist
    -0.06
     }],↵
    -0.06
    POSITIVE LOGITS
    stub
    0.07
    ディア
    0.07
     개발
    0.06
    です
    0.06
    ADB
    0.06
    瓦
    0.06
     inmate
    0.06
     百度收录
    0.06
     Patch
    0.06
    -pencil
    0.06
    Act Density 0.013%

    No Known Activations