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

    Neuronpedia

    INDEX
    Explanations

    code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    authorize
    -0.07
     extensively
    -0.06
    PL
    -0.06
     grid
    -0.06
     Governments
    -0.06
    rnd
    -0.06
    　　　　　　　
    -0.06
     -*-
↵
    -0.06
     Middleton
    -0.06
    ＿＿＿＿
    -0.06
    POSITIVE LOGITS
    Shoot
    0.08
     Spell
    0.07
    Shared
    0.07
     взрос
    0.07
     SLOT
    0.06
     топ
    0.06
    TouchListener
    0.06
     kitten
    0.06
     venda
    0.06
     inflict
    0.06
    Act Density 0.050%

    No Known Activations