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

    Neuronpedia

    INDEX
    Explanations

    oste

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offend
    -0.08
    📘
    -0.08
    cluding
    -0.07
    Ⲩ
    -0.07
    杵
    -0.07
    @Web
    -0.07
    请注意
    -0.06
    _ELEMENTS
    -0.06
    挚
    -0.06
    Unsupported
    -0.06
    POSITIVE LOGITS
     aproxim
    0.07
    _advance
    0.07
    squ
    0.07
    )
↵
    0.07
    ++){
    0.07
    *>
    0.07
     practices
    0.07
    ')↵
    0.07
    индив
    0.07
    ){
↵
    0.07
    Act Density 0.027%

    No Known Activations