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

    Neuronpedia

    INDEX
    Explanations

    Pausing or waiting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ضا
    -0.07
     �
    -0.07
    ΡΓ
    -0.06
     країни
    -0.06
     برق
    -0.06
    ansom
    -0.06
     میلادی
    -0.06
    andro
    -0.06
    getc
    -0.06
    .java
    -0.06
    POSITIVE LOGITS
     Monday
    0.07
     Wednesday
    0.07
    atching
    0.06
     Saturday
    0.06
     Southeast
    0.06
     estimation
    0.06
     Tickets
    0.06
    illegal
    0.06
     Thursday
    0.06
     incorrectly
    0.06
    Act Density 0.008%

    No Known Activations