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

    Neuronpedia

    INDEX
    Explanations

    definitions of new words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sales
    -0.07
    載
    -0.07
    .isChecked
    -0.07
    .Page
    -0.07
     Die
    -0.06
    plně
    -0.06
    opers
    -0.06
    ornecedor
    -0.06
     Flynn
    -0.06
    ),
    -0.06
    POSITIVE LOGITS
     serene
    0.06
     minim
    0.06
    unu
    0.06
    กรรมการ
    0.06
     adress
    0.06
    +","+
    0.06
     inclus
    0.06
     �
    0.06
     кис
    0.06
     coorden
    0.06
    Act Density 0.016%

    No Known Activations