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

    Neuronpedia

    INDEX
    Explanations

    Actions are happening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onds
    -0.06
    gin
    -0.06
     dere
    -0.06
     голову
    -0.06
     Christmas
    -0.06
    db
    -0.06
     Chan
    -0.06
     Theater
    -0.06
    (split
    -0.06
    Limit
    -0.06
    POSITIVE LOGITS
    ента
    0.07
    uede
    0.07
    !");↵
    0.06
    #:
    0.06
     đến
    0.06
     Kotlin
    0.06
    ++)↵
    0.06
    eterminate
    0.06
    �
    0.06
     concl
    0.06
    Act Density 0.016%

    No Known Activations