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

    Neuronpedia

    INDEX
    Explanations

    Snippets of longer pieces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alars
    -0.07
     pillows
    -0.06
    등
    -0.06
     gsl
    -0.06
    eceği
    -0.06
    .clients
    -0.06
    .assertThat
    -0.06
     analytic
    -0.06
    (UUID
    -0.06
     positivity
    -0.06
    POSITIVE LOGITS
    \Column
    0.07
    �藏
    0.07
     Fully
    0.06
     Blender
    0.06
    .now
    0.06
    学生
    0.06
    ({↵
    0.06
    长
    0.06
    Motor
    0.06
     createState
    0.06
    Act Density 0.001%

    No Known Activations