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

    Neuronpedia

    INDEX
    Explanations

    introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laptop
    -0.07
     vert
    -0.07
    	Use
    -0.07
     cycles
    -0.06
    �
    -0.06
     polling
    -0.06
     checkpoints
    -0.06
     Soviet
    -0.06
     legisl
    -0.06
    -cons
    -0.06
    POSITIVE LOGITS
     introductory
    0.09
     intro
    0.08
     introduction
    0.07
     Invitation
    0.07
     Monroe
    0.07
    meric
    0.07
    ologie
    0.07
    .Complete
    0.07
    imo
    0.07
     Introduction
    0.06
    Act Density 0.014%

    No Known Activations