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

    Neuronpedia

    INDEX
    Explanations

    interrupted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nicht
    -0.06
     Dirt
    -0.06
     Pitch
    -0.06
     circumcision
    -0.06
     OTP
    -0.06
    .Batch
    -0.06
    $status
    -0.06
    debian
    -0.06
     dveře
    -0.05
    people
    -0.05
    POSITIVE LOGITS
    Sum
    0.08
     interrupted
    0.08
     LogManager
    0.07
     peacefully
    0.06
    boom
    0.06
    汇
    0.06
     geschichten
    0.06
    Chat
    0.06
    อากาศ
    0.06
     interrupts
    0.06
    Act Density 0.009%

    No Known Activations