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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    哧
    -0.07
    情人节
    -0.07
    昡
    -0.07
    senal
    -0.06
     cil
    -0.06
    Modificar
    -0.06
    Guide
    -0.06
    蹦
    -0.06
     вы
    -0.06
     award
    -0.06
    POSITIVE LOGITS
     accum
    0.07
    Schema
    0.07
    .servers
    0.07
    (employee
    0.06
     لأنه
    0.06
    .Pages
    0.06
     ws
    0.06
    External
    0.06
     flows
    0.06
    Proto
    0.06
    Act Density 0.002%

    No Known Activations