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

    Neuronpedia

    INDEX
    Explanations

    After

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.66
    pidou
    -0.66
    kheim
    -0.64
     chariots
    -0.63
    @[+][
    -0.58
     eventdata
    -0.57
    EIP
    -0.57
     فريبيس
    -0.57
    itattu
    -0.56
    Diweddarwch
    -0.56
    POSITIVE LOGITS
     you
    0.94
    you
    0.77
    pay
    0.57
    care
    0.53
     podéis
    0.50
     particulières
    0.50
     vous
    0.50
     YOU
    0.49
     vosotros
    0.47
    You
    0.47
    Act Density 0.008%

    No Known Activations