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

    Neuronpedia

    INDEX
    Explanations

    handle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beige
    -0.07
     CONTROL
    -0.06
     redesign
    -0.06
     halo
    -0.06
     puck
    -0.06
     Hazard
    -0.06
    自身
    -0.06
    zf
    -0.06
     سی
    -0.06
    post
    -0.06
    POSITIVE LOGITS
     MethodInfo
    0.06
    learner
    0.06
    .transaction
    0.06
     tecn
    0.06
    .Lib
    0.06
     JSGlobal
    0.06
    Flexible
    0.06
     JsonResult
    0.06
    と思う
    0.06
    objc
    0.06
    Act Density 0.000%

    No Known Activations