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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "github
    -0.07
     Chocolate
    -0.07
     queryString
    -0.06
     xứ
    -0.06
     financing
    -0.06
    .queue
    -0.06
     \"%
    -0.06
    consin
    -0.06
    chlor
    -0.06
     Shopping
    -0.06
    POSITIVE LOGITS
    ATURE
    0.07
    ,rp
    0.07
     فرزند
    0.06
    υσ
    0.06
    abra
    0.06
     prov
    0.06
     elimination
    0.06
    atures
    0.06
     безопасности
    0.06
     consumo
    0.06
    Act Density 0.099%

    No Known Activations