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

    Neuronpedia

    INDEX
    Explanations

    you're thinking something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,A
    -0.07
     olmak
    -0.07
    aucoup
    -0.07
     黄
    -0.07
    IVE
    -0.06
     taky
    -0.06
    	H
    -0.06
    混合
    -0.06
    _ids
    -0.06
     Lightweight
    -0.06
    POSITIVE LOGITS
     Gauss
    0.08
     sed
    0.07
    .AutoScale
    0.07
    Você
    0.06
     специалист
    0.06
    Vous
    0.06
     refute
    0.06
     nan
    0.06
     Jae
    0.06
     �
    0.05
    Act Density 0.039%

    No Known Activations