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

    Neuronpedia

    INDEX
    Explanations

    code or instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wheat
    -0.06
     FHA
    -0.06
     tiles
    -0.06
    anye
    -0.06
    桥
    -0.06
     Ideal
    -0.06
    aphore
    -0.06
    .userID
    -0.06
    insi
    -0.06
     ایران
    -0.06
    POSITIVE LOGITS
     frankfurt
    0.07
    ERGE
    0.07
    -match
    0.07
    ercial
    0.06
     viêm
    0.06
     downright
    0.06
    丶
    0.06
     será
    0.06
    Fitness
    0.06
     confidential
    0.06
    Act Density 0.130%

    No Known Activations