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

    Neuronpedia

    INDEX
    Explanations

    Elm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sat
    -0.08
    è
    -0.07
    Weights
    -0.07
    ='<?
    -0.06
     радян
    -0.06
    uju
    -0.06
     호
    -0.06
    ทะ
    -0.06
     Bukkit
    -0.06
     sim
    -0.06
    POSITIVE LOGITS
     elm
    0.06
    .INSTANCE
    0.06
     EMS
    0.06
    ↵ ↵
    0.06
    mn
    0.06
    ably
    0.06
     диаг
    0.06
    avelength
    0.06
    Để
    0.06
     Applying
    0.06
    Act Density 0.003%

    No Known Activations