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

    Neuronpedia

    INDEX
    Explanations

    short

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sid
    -0.07
    🗒
    -0.06
     jos
    -0.06
    .FieldName
    -0.06
    卷
    -0.06
     Bucks
    -0.06
    矜
    -0.06
    初中
    -0.06
    �
    -0.06
    Attr
    -0.06
    POSITIVE LOGITS
    CurrentUser
    0.07
     pneumonia
    0.07
    fontSize
    0.07
     silenced
    0.07
    黎明
    0.07
     Empresa
    0.07
    urgy
    0.06
     Rihanna
    0.06
    _LT
    0.06
     Ratio
    0.06
    Act Density 0.005%

    No Known Activations