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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruler
    -0.07
    bour
    -0.07
    iver
    -0.07
    inka
    -0.07
    -ver
    -0.06
     Rocky
    -0.06
    dh
    -0.06
     Cake
    -0.06
    Kitchen
    -0.06
     司
    -0.06
    POSITIVE LOGITS
    Subscriber
    0.07
     góp
    0.07
     Üst
    0.06
     Lug
    0.06
     Annotation
    0.06
     hans
    0.06
     happened
    0.06
     serão
    0.06
     Specifies
    0.06
    _AT
    0.06
    Act Density 0.150%

    No Known Activations