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

    Neuronpedia

    INDEX
    Explanations

    evacuations and new concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #+#
    -0.63
     NSCoder
    -0.62
    setVerticalGroup
    -0.59
     nitrogen
    -0.59
    AccessorTable
    -0.57
    endphp
    -0.51
    urnum
    -0.50
     مشين
    -0.50
    Geplaatst
    -0.49
     estekak
    -0.49
    POSITIVE LOGITS
    ness
    0.74
    nya
    0.63
    ly
    0.63
     ſhe
    0.59
     againſt
    0.56
    sible
    0.54
    Rui
    0.54
     DKK
    0.54
    __(/*!
    0.53
    re
    0.52
    Act Density 0.102%

    No Known Activations