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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apist
    -0.07
    Concept
    -0.07
    تماد
    -0.07
    ￣￣
    -0.07
    Labels
    -0.07
    Hold
    -0.07
    ￣￣￣
    -0.06
    -New
    -0.06
     наяв
    -0.06
     ویرایش
    -0.06
    POSITIVE LOGITS
    jectory
    0.07
     trainable
    0.07
    STYLE
    0.06
     chy
    0.06
    particularly
    0.06
    �
    0.06
     Knowledge
    0.06
     responsibility
    0.06
    Rot
    0.06
     lastIndex
    0.06
    Act Density 0.002%

    No Known Activations