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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Automation
    -0.07
     المص
    -0.07
    reserved
    -0.07
    _builder
    -0.07
    69
    -0.07
     pixmap
    -0.06
     diver
    -0.06
     mower
    -0.06
     바로
    -0.06
     تخ
    -0.06
    POSITIVE LOGITS
     vf
    0.07
     avait
    0.06
    AILY
    0.06
     enim
    0.06
    Ensure
    0.06
     Essential
    0.06
    olvimento
    0.06
     shall
    0.06
     ni
    0.06
     нового
    0.05
    Act Density 0.140%

    No Known Activations