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

    Neuronpedia

    INDEX
    Explanations

    creative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Formula
    -0.08
     anni
    -0.07
    Travel
    -0.06
     anderen
    -0.06
    ignty
    -0.06
     addChild
    -0.06
    níků
    -0.06
     traversal
    -0.06
    ipeline
    -0.06
     furnace
    -0.06
    POSITIVE LOGITS
     Orlando
    0.07
    wiąz
    0.06
     tad
    0.06
     Gins
    0.06
    .getRaw
    0.06
     широк
    0.06
    슴
    0.06
    tingham
    0.06
    angement
    0.06
    welcome
    0.06
    Act Density 0.282%

    No Known Activations