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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    41
    -0.07
    леч
    -0.07
    ・━・━
    -0.07
    VILLE
    -0.06
     pinterest
    -0.06
     FM
    -0.06
     Device
    -0.06
    arias
    -0.06
     Saturday
    -0.06
     MT
    -0.06
    POSITIVE LOGITS
    玄
    0.06
     genom
    0.06
    งเป
    0.06
    .ver
    0.06
    더
    0.06
    것
    0.06
     republiky
    0.06
    韓
    0.06
    ický
    0.06
     kadar
    0.06
    Act Density 0.101%

    No Known Activations