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

    Neuronpedia

    INDEX
    Explanations

    Explanations and arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    like
    -0.07
    beautiful
    -0.07
     Oktober
    -0.06
    Recipes
    -0.06
     dược
    -0.06
    !
    -0.06
     victim
    -0.06
    different
    -0.06
     chic
    -0.06
     Scotch
    -0.06
    POSITIVE LOGITS
     denne
    0.07
     dirección
    0.06
    ดร
    0.06
    €€€€€€€€
    0.06
     免
    0.06
    handled
    0.06
     Serge
    0.06
     distort
    0.06
    .AppendFormat
    0.06
    πουργ
    0.06
    Act Density 0.096%

    No Known Activations