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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Opportunity
    -0.06
    -0.06
     lvl
    -0.06
     القر
    -0.06
    \Array
    -0.06
     полов
    -0.06
    -city
    -0.06
    ZF
    -0.06
     poetic
    -0.06
     mejorar
    -0.06
    POSITIVE LOGITS
     Ack
    0.07
     Hermes
    0.07
     bishop
    0.07
     bude
    0.07
     xyz
    0.06
    ,[
    0.06
     Jade
    0.06
     sig
    0.06
     -->
    0.06
    Nuitka
    0.06
    Act Density 0.000%

    No Known Activations