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

    Neuronpedia

    INDEX
    Explanations

    paper introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blast
    -0.07
    antan
    -0.06
    flake
    -0.06
     Бі
    -0.06
    вать
    -0.06
    "w
    -0.06
    였다
    -0.06
    mada
    -0.06
    une
    -0.06
    结
    -0.06
    POSITIVE LOGITS
    .PR
    0.07
     Epoch
    0.06
    ToArray
    0.06
     unins
    0.06
    Segment
    0.06
     endure
    0.06
     нада
    0.06
     termination
    0.06
    selectorMethod
    0.06
    IMPLIED
    0.06
    Act Density 0.001%

    No Known Activations