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

    Neuronpedia

    INDEX
    Explanations

    conveying

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     di
    -0.07
     בתחום
    -0.07
    成了
    -0.07
    始め
    -0.07
     rectangular
    -0.07
    Editar
    -0.07
    限制
    -0.07
    了起来
    -0.07
     dotyczące
    -0.07
    反思
    -0.07
    POSITIVE LOGITS
     voice
    0.07
    怖
    0.07
     IMD
    0.07
     {/*
    0.06
     actresses
    0.06
    Photon
    0.06
    فاق
    0.06
    }});↵
    0.06
    蜮
    0.06
    揳
    0.06
    Act Density 0.008%

    No Known Activations