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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ipairs
    -0.07
     necessário
    -0.07
    𝔼
    -0.07
     resemble
    -0.06
     препарат
    -0.06
     specifier
    -0.06
     tính
    -0.06
    .primary
    -0.06
    羡
    -0.06
    確か
    -0.06
    POSITIVE LOGITS
    pop
    0.07
     Camping
    0.07
     Routes
    0.07
    income
    0.07
    (rd
    0.07
    vent
    0.06
    energy
    0.06
    Spy
    0.06
    �
    0.06
     glam
    0.06
    Act Density 0.002%

    No Known Activations