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

    Neuronpedia

    INDEX
    Explanations

    descriptive scenarios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Jwt
    -0.09
     quint
    -0.08
    债
    -0.08
    .SQLite
    -0.08
    Period
    -0.08
     Pension
    -0.08
    .JWT
    -0.08
    .Program
    -0.08
     pension
    -0.08
    Lessons
    -0.08
    POSITIVE LOGITS
     sprayed
    0.11
     yell
    0.11
     grime
    0.10
     весел
    0.10
     hilarious
    0.10
     mayonnaise
    0.10
     slime
    0.10
     гряз
    0.10
     redness
    0.10
     clothing
    0.10
    Act Density 0.014%

    No Known Activations