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

    Neuronpedia

    INDEX
    Explanations

    biology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chart
    -0.06
    (first
    -0.06
     prz
    -0.06
    star
    -0.06
     Vir
    -0.06
     guerr
    -0.06
     House
    -0.06
     comun
    -0.06
    StepThrough
    -0.06
     Guar
    -0.06
    POSITIVE LOGITS
     biology
    0.12
     Biology
    0.10
     biologist
    0.08
    Authentication
    0.08
     Biol
    0.07
    bio
    0.07
     BIO
    0.07
     Anatomy
    0.06
    .Big
    0.06
    Say
    0.06
    Act Density 0.005%

    No Known Activations