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

    Neuronpedia

    INDEX
    Explanations

    arrows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GPU
    -0.08
     Amir
    -0.07
     الخار
    -0.07
    _imgs
    -0.07
    转入
    -0.07
    公共资源
    -0.07
    .HashMap
    -0.07
     гол
    -0.07
    半个月
    -0.07
     flawless
    -0.07
    POSITIVE LOGITS
    	Mono
    0.06
    Filename
    0.06
    uju
    0.06
    شي
    0.06
    ografia
    0.06
    very
    0.06
    jem
    0.06
    ビー
    0.06
    agenda
    0.06
     zap
    0.06
    Act Density 0.000%

    No Known Activations