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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     learned
    -0.07
     أف
    -0.07
    /head
    -0.07
    �
    -0.07
     joining
    -0.07
    مراج
    -0.07
    مراجعة
    -0.07
     também
    -0.07
    重温
    -0.07
    .collection
    -0.06
    POSITIVE LOGITS
     [[[
    0.08
    ↕
    0.07
    Automatic
    0.07
    まり
    0.07
    姊
    0.07
    נית
    0.06
    dbg
    0.06
    閱
    0.06
     UPS
    0.06
     //(
    0.06
    Act Density 0.001%

    No Known Activations