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

    Neuronpedia

    INDEX
    Explanations

    Repeating dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crescent
    -0.07
     Thesis
    -0.07
     Appe
    -0.07
     Fro
    -0.06
     Standards
    -0.06
     Purple
    -0.06
    �
    -0.06
     retirement
    -0.06
     resposta
    -0.06
     predictive
    -0.06
    POSITIVE LOGITS
    iaz
    0.06
     bordel
    0.06
    tek
    0.06
    ि,
    0.06
    ực
    0.06
    .term
    0.06
     slack
    0.06
     ох
    0.06
    /todo
    0.06
     ail
    0.06
    Act Density 0.003%

    No Known Activations