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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Edit
    -0.07
    eliac
    -0.06
     Vet
    -0.06
    طال
    -0.06
     बनन
    -0.06
    Paths
    -0.06
    σιεύ
    -0.06
    ][
    -0.06
    lum
    -0.06
    нат
    -0.06
    POSITIVE LOGITS
     Mr
    0.07
    Mr
    0.07
     assists
    0.06
     Thermal
    0.06
     refunds
    0.06
     regeneration
    0.06
    clas
    0.06
     Thread
    0.06
    (Document
    0.06
    .Password
    0.06
    Act Density 0.008%

    No Known Activations