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

    Neuronpedia

    INDEX
    Explanations

    Referencing pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bilim
    -0.07
    "d
    -0.07
    .Rest
    -0.07
     reklam
    -0.07
    スマ
    -0.07
     Seat
    -0.06
    �
    -0.06
    änge
    -0.06
     Bean
    -0.06
    calcul
    -0.06
    POSITIVE LOGITS
    _partitions
    0.07
    <Key
    0.06
     acronym
    0.06
     mistakes
    0.06
     Reply
    0.06
     crack
    0.06
     Adopt
    0.06
     jugador
    0.06
     &#
    0.06
     what
    0.06
    Act Density 0.097%

    No Known Activations