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

    Neuronpedia

    INDEX
    Explanations

    always

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MF
    -0.07
     Saturdays
    -0.07
     parchment
    -0.06
    根本
    -0.06
    close
    -0.06
    MMM
    -0.06
     mejores
    -0.06
     shipments
    -0.06
     manager
    -0.06
    .exam
    -0.06
    POSITIVE LOGITS
     createTime
    0.07
    rava
    0.07
    .KeyEvent
    0.06
     Slovenia
    0.06
    .Area
    0.06
    -reaching
    0.06
    ricula
    0.06
    τύ
    0.06
    ustomed
    0.06
    @author
    0.06
    Act Density 0.041%

    No Known Activations