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

    Neuronpedia

    INDEX
    Explanations

    span

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (response
    -0.09
    为了
    -0.07
     dolphins
    -0.07
     dolphin
    -0.07
    EOS
    -0.07
    🔛
    -0.06
    盎
    -0.06
     cambio
    -0.06
    👟
    -0.06
    前一天
    -0.06
    POSITIVE LOGITS
    暶
    0.07
     Grad
    0.07
     Cassidy
    0.07
    =\""
    0.07
     Band
    0.07
     fro
    0.07
     Bret
    0.07
     있다고
    0.07
    	Schema
    0.07
     Push
    0.07
    Act Density 0.000%

    No Known Activations