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

    Neuronpedia

    INDEX
    Explanations

    Number ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，要
    -0.07
     amis
    -0.07
    似的
    -0.07
    με
    -0.07
     ptr
    -0.06
    ють
    -0.06
    Liked
    -0.06
    ’all
    -0.06
    せる
    -0.06
     آمده
    -0.06
    POSITIVE LOGITS
     messaging
    0.06
     handful
    0.06
    LL
    0.06
    <Integer
    0.06
     Vik
    0.06
     termination
    0.06
     Messages
    0.06
                    ↵
    0.06
     Ник
    0.06
    .carousel
    0.06
    Act Density 0.005%

    No Known Activations