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

    Neuronpedia

    INDEX
    Explanations

    pl

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     deposit
    -0.07
     fuss
    -0.07
     signup
    -0.06
    かれ
    -0.06
     bikes
    -0.06
    想去
    -0.06
    deps
    -0.06
     Buy
    -0.06
     employee
    -0.06
     --------------------------------------------------------------------------------
    -0.06
    POSITIVE LOGITS
    學
    0.07
    ﺂ
    0.07
     empres
    0.07
     factura
    0.07
    NDAR
    0.07
     Fib
    0.06
    ﻂ
    0.06
    ガイド
    0.06
     COMPUT
    0.06
    مدار
    0.06
    Act Density 0.008%

    No Known Activations