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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kwe
    -0.08
    mee
    -0.07
    -0.07
    maga
    -0.07
     Thrive
    -0.07
     निर्देशन
    -0.07
    �
    -0.07
     विजय
    -0.07
     maga
    -0.07
    mek
    -0.07
    POSITIVE LOGITS
    究
    0.08
    கர்
    0.07
     ધ્યાન
    0.07
    istema
    0.07
    Notation
    0.07
     Rational
    0.07
    ாமல்
    0.07
     rapaz
    0.07
    amus
    0.07
     approaches
    0.07
    Act Density 0.158%
    No Known Activations