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

    Neuronpedia

    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lives
    -0.06
     progressBar
    -0.06
    Woman
    -0.06
    Watching
    -0.06
     tapes
    -0.06
    .Packet
    -0.06
    phoneNumber
    -0.06
    managedType
    -0.06
     seas
    -0.06
     Eduardo
    -0.06
    POSITIVE LOGITS
     HY
    0.07
     SAY
    0.07
     Def
    0.06
    Рё
    0.06
    acy
    0.06
    iếng
    0.06
     дека
    0.06
     BILL
    0.06
    则
    0.06
    IF
    0.06
    Act Density 0.015%

    No Known Activations