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

    Neuronpedia

    INDEX
    Explanations

    closed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ens
    -0.07
    +(\
    -0.07
     sounding
    -0.07
    _teacher
    -0.07
    _Local
    -0.06
    Even
    -0.06
     fees
    -0.06
    izacion
    -0.06
     président
    -0.06
    readOnly
    -0.06
    POSITIVE LOGITS
     ply
    0.06
    _CANCEL
    0.06
    иль
    0.06
    _section
    0.06
     프로
    0.06
    ransition
    0.06
    роиз
    0.06
     oppressive
    0.06
    ANTLR
    0.06
    bsp
    0.06
    Act Density 0.054%

    No Known Activations