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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Electron
    -0.28
    èij¡
    -0.26
    缴
    -0.25
    çļĦè¦ģæ±Ĥ
    -0.25
    ror
    -0.25
    Homepage
    -0.25
    electron
    -0.25
     electron
    -0.25
    .lu
    -0.24
    indow
    -0.24
    POSITIVE LOGITS
     worked
    0.27
    Invariant
    0.25
     nhiên
    0.25
    åıªèĥ½è¯´
    0.24
    毡
    0.24
     saja
    0.24
     invariant
    0.24
    iam
    0.24
     em
    0.23
     played
    0.23
    Act Density 0.002%

    No Known Activations