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

    Neuronpedia

    INDEX
    Explanations

    say "l word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ellites
    -0.07
    �
    -0.07
    的各种
    -0.07
     השלישי
    -0.07
    مركز
    -0.07
    上周
    -0.07
    ambique
    -0.06
    ألو
    -0.06
    短期内
    -0.06
    go
    -0.06
    POSITIVE LOGITS
    .makeText
    0.08
    .disc
    0.07
    晞
    0.07
     TRACE
    0.07
     Disclosure
    0.07
    勰
    0.07
     wym
    0.07
    سي
    0.07
     SJ
    0.07
    ='%
    0.06
    Act Density 0.007%

    No Known Activations