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

    Neuronpedia

    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NUM
    -0.07
    JS
    -0.06
     Wise
    -0.06
    クト
    -0.06
    Word
    -0.06
     svým
    -0.06
    hangi
    -0.06
     мик
    -0.06
    �
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    (Entity
    0.07
     Deployment
    0.07
    obic
    0.07
     duplicated
    0.06
    àng
    0.06
     tower
    0.06
     diabetic
    0.06
    (per
    0.06
     Specialist
    0.06
    治疗
    0.06
    Act Density 0.001%

    No Known Activations