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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -roll
    -0.07
     البحر
    -0.07
     ",");↵
    -0.07
    750
    -0.07
    .he
    -0.07
     deceit
    -0.07
    ์ค
    -0.07
    idad
    -0.06
    ราค
    -0.06
    ुछ
    -0.06
    POSITIVE LOGITS
    MH
    0.06
     periods
    0.06
    transform
    0.06
     cms
    0.06
     tonight
    0.06
    شمالی
    0.06
    apiKey
    0.06
     Appalachian
    0.06
     creative
    0.06
    RequestParam
    0.06
    Act Density 0.004%

    No Known Activations