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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VLAN
    -0.07
     {%
    -0.07
     Heading
    -0.07
     Lös
    -0.07
     ма
    -0.07
     Props
    -0.07
     Screening
    -0.07
     anxious
    -0.07
     течение
    -0.07
    纪委
    -0.07
    POSITIVE LOGITS
     intended
    0.07
    //↵↵
    0.07
    Coeff
    0.07
    :**
    0.07
    ??
    0.07
    廣
    0.07
    MouseClicked
    0.07
    ():
↵
    0.06
    Modify
    0.06
    .''
    0.06
    Act Density 0.027%

    No Known Activations