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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orb
    -0.06
    .WEST
    -0.06
    Conta
    -0.06
     Lennon
    -0.06
    VG
    -0.06
     thế
    -0.06
    999
    -0.06
    Western
    -0.06
    -<?
    -0.06
    MethodInfo
    -0.06
    POSITIVE LOGITS
     representation
    0.07
     Exp
    0.07
     initialize
    0.07
     overlook
    0.07
    ;}↵↵
    0.07
    流
    0.06
     among
    0.06
     ヴ
    0.06
     impr
    0.06
    لاح
    0.06
    Act Density 0.002%

    No Known Activations