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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     throttle
    -0.06
     dvěma
    -0.06
     Rugby
    -0.06
    .getHeight
    -0.06
    grow
    -0.06
     Thai
    -0.06
     Migration
    -0.06
     Poker
    -0.06
     accreditation
    -0.06
     Huffman
    -0.06
    POSITIVE LOGITS
    ować
    0.07
    �
    0.07
    保险
    0.07
    ευση
    0.06
    �
    0.06
    頂
    0.06
    ุณ
    0.06
     Prot
    0.06
     تس
    0.06
     {}",
    0.06
    Act Density 0.025%

    No Known Activations