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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Json
    -0.06
    topics
    -0.06
     partisan
    -0.06
    温度
    -0.06
    θεν
    -0.06
    girl
    -0.06
     pork
    -0.06
    rch
    -0.06
     savings
    -0.06
     recursion
    -0.06
    POSITIVE LOGITS
    {}↵
    0.08
     вив
    0.07
     nada
    0.07
     lazım
    0.07
    acht
    0.06
    ント
    0.06
    avia
    0.06
     ciz
    0.06
     l�
    0.06
    DNS
    0.06
    Act Density 0.096%

    No Known Activations