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

    Neuronpedia

    INDEX
    Explanations

    template

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aravel
    -0.07
    Ts
    -0.06
     галузі
    -0.06
     sue
    -0.06
     narr
    -0.06
     Azure
    -0.06
     Uzbek
    -0.06
    ‏
    -0.06
     melt
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    orses
    0.08
    (renderer
    0.07
     needed
    0.07
    ตร
    0.06
     진짜
    0.06
    aising
    0.06
    ]+\
    0.06
    ycles
    0.06
    <State
    0.06
    natural
    0.06
    Act Density 0.001%

    No Known Activations