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

    Neuronpedia

    INDEX
    Explanations

    preaching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .User
    -0.07
     چرا
    -0.07
     Bukkit
    -0.07
     Memories
    -0.06
    udem
    -0.06
    OT
    -0.06
    .alias
    -0.06
    лиш
    -0.06
     Scots
    -0.06
    ataloader
    -0.06
    POSITIVE LOGITS
     outfits
    0.07
    (confirm
    0.06
    27
    0.06
    tv
    0.06
     mm
    0.06
    ,w
    0.06
     Pred
    0.06
     超
    0.06
    eventName
    0.06
     Capac
    0.06
    Act Density 0.026%

    No Known Activations