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

    Neuronpedia

    INDEX
    Explanations

    scientific explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    дет
    -0.08
    OutputStream
    -0.07
    _validator
    -0.06
    	Delete
    -0.06
    \Html
    -0.06
     CONTROL
    -0.06
     nemá
    -0.06
    orsk
    -0.06
     Zd
    -0.06
    organized
    -0.06
    POSITIVE LOGITS
    _hat
    0.06
     caveat
    0.06
    Direccion
    0.06
     annihil
    0.06
    ạy
    0.06
     gutter
    0.06
    ा-
    0.06
    /train
    0.06
    ricane
    0.06
     investigating
    0.06
    Act Density 0.134%

    No Known Activations