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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kindle
    -0.07
     setState
    -0.07
     SDS
    -0.07
    求助
    -0.07
    Ὸ
    -0.07
    非常喜欢
    -0.07
     toxins
    -0.07
     Dude
    -0.07
    省政府
    -0.07
    ۇ
    -0.07
    POSITIVE LOGITS
     있을
    0.08
    ificar
    0.07
     {
↵
    0.07
    _NORMAL
    0.07
     עסקי
    0.07
    .Link
    0.07
     nào
    0.07
     La
    0.07
     {↵
    0.07
    ()){
↵
    0.06
    Act Density 0.081%

    No Known Activations