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
     sud
    -0.07
    elloworld
    -0.07
    asters
    -0.06
     flags
    -0.06
     Disable
    -0.06
     generar
    -0.06
     Standing
    -0.06
    wjgl
    -0.06
     Darkness
    -0.06
    erreur
    -0.06
    POSITIVE LOGITS
    dex
    0.07
     IOException
    0.07
    ISTRIBUT
    0.07
    .teacher
    0.06
    ...↵↵↵↵↵↵
    0.06
    色
    0.06
    mom
    0.06
    translations
    0.06
    Asked
    0.06
    !↵↵↵↵↵↵
    0.06
    Act Density 0.004%

    No Known Activations