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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chu
    -0.07
     �
    -0.07
     як
    -0.06
    estr
    -0.06
    minster
    -0.06
    749
    -0.06
    uky
    -0.06
    roit
    -0.06
    ён
    -0.06
     Uy
    -0.06
    POSITIVE LOGITS
    (inputStream
    0.07
    payload
    0.07
    课
    0.06
    Originally
    0.06
    ##
    0.06
    =msg
    0.06
    ！",
    0.06
     《
    0.06
    .amazon
    0.06
    Sept
    0.06
    Act Density 0.030%

    No Known Activations