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
     욕
    -0.07
     Seats
    -0.07
     objectMapper
    -0.07
     Dwarf
    -0.06
    (horizontal
    -0.06
     心
    -0.06
     vest
    -0.06
    103
    -0.06
     Snake
    -0.06
     Antwort
    -0.06
    POSITIVE LOGITS
    кие
    0.08
     ARISING
    0.07
    �n
    0.07
    ihan
    0.07
    IGIN
    0.06
     injustice
    0.06
    unsqueeze
    0.06
    сок
    0.06
    만원입니다
    0.06
    =out
    0.06
    Act Density 0.110%

    No Known Activations