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
     ま
    -0.08
    .data
    -0.07
     보내
    -0.07
    =event
    -0.07
    ModelError
    -0.07
    !I
    -0.07
     Ή
    -0.07
    	My
    -0.07
    _ENSURE
    -0.06
    ###############################################################################↵
    -0.06
    POSITIVE LOGITS
     Sierra
    0.06
     PPC
    0.06
    osing
    0.06
     област
    0.06
     patriot
    0.06
     forest
    0.06
     Cases
    0.06
     متف
    0.05
    -live
    0.05
    uled
    0.05
    Act Density 0.009%

    No Known Activations