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

    Neuronpedia

    INDEX
    Explanations

    Dev

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מומחי
    -0.08
     of
    -0.08
     Arnold
    -0.07
     Noticed
    -0.07
    <Student
    -0.07
     xbox
    -0.07
     jealousy
    -0.07
     Assignment
    -0.07
    ﾟ
    -0.07
    .Long
    -0.06
    POSITIVE LOGITS
    คะแน
    0.08
    _mut
    0.08
    皱纹
    0.08
    Meta
    0.07
     devastated
    0.07
    яти
    0.07
    邑
    0.07
    ->{
    0.07
    Inflater
    0.07
    dev
    0.07
    Act Density 0.012%

    No Known Activations