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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cate
    -0.07
    -di
    -0.07
    Articles
    -0.07
    孩子
    -0.07
     advises
    -0.07
    ительным
    -0.07
    -Y
    -0.06
     predicted
    -0.06
     Beds
    -0.06
     Logic
    -0.06
    POSITIVE LOGITS
    evi
    0.07
     onPress
    0.06
    (Byte
    0.06
     ενός
    0.06
    .ravel
    0.06
    Utc
    0.06
     firestore
    0.06
    /datatables
    0.06
    !==
    0.06
    methodPointerType
    0.06
    Act Density 0.000%

    No Known Activations