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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    task
    -0.07
    prot
    -0.06
    Materials
    -0.06
     itching
    -0.06
     Worldwide
    -0.06
    Database
    -0.06
    dac
    -0.06
    Ž
    -0.06
    arro
    -0.06
    SW
    -0.06
    POSITIVE LOGITS
    ASTER
    0.07
    ْس
    0.07
     هم
    0.06
     работы
    0.06
    Collapsed
    0.06
    나는
    0.06
     dél
    0.06
    itaire
    0.06
     вс
    0.06
     probable
    0.06
    Act Density 0.006%

    No Known Activations