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

    Neuronpedia

    INDEX
    Explanations

    Exploration/Introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Christmas
    -0.06
    crast
    -0.06
    (File
    -0.06
     хвор
    -0.06
     contenders
    -0.06
    actice
    -0.06
    loo
    -0.06
    ud
    -0.06
     ride
    -0.06
    otta
    -0.05
    POSITIVE LOGITS
    |required
    0.08
     ai
    0.07
     abaixo
    0.07
     temiz
    0.07
     trung
    0.07
    بع
    0.07
     Não
    0.07
    ´t
    0.07
     Emb
    0.06
    usz
    0.06
    Act Density 0.061%

    No Known Activations