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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grid
    -0.07
     Engagement
    -0.07
    Hours
    -0.07
    -Con
    -0.06
     Generation
    -0.06
     WEB
    -0.06
    局
    -0.06
     diffusion
    -0.06
     layer
    -0.06
     Authority
    -0.06
    POSITIVE LOGITS
     apellido
    0.08
    apellido
    0.07
     gluten
    0.07
     surname
    0.07
     parm
    0.06
     lname
    0.06
    bara
    0.06
    .wrap
    0.06
     hypoth
    0.06
    ellidos
    0.06
    Act Density 0.011%

    No Known Activations