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

    Neuronpedia

    INDEX
    Explanations

    la

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lev
    -0.07
     movements
    -0.07
    tro
    -0.07
    technical
    -0.07
    "title
    -0.07
     polarization
    -0.06
    GPU
    -0.06
     emiss
    -0.06
    abyrinth
    -0.06
     COMPUTER
    -0.06
    POSITIVE LOGITS
     more
    0.07
     mehr
    0.07
     більше
    0.07
    qm
    0.06
    -more
    0.06
    的一个
    0.06
    更多
    0.06
    .condition
    0.06
     kost
    0.06
     further
    0.06
    Act Density 0.022%

    No Known Activations