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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rams
    -0.07
    Un
    -0.07
     Lawyers
    -0.06
    eren
    -0.06
    GitHub
    -0.06
     delegation
    -0.06
    (Date
    -0.06
    альных
    -0.06
    Domains
    -0.06
     домов
    -0.06
    POSITIVE LOGITS
    юсь
    0.07
    меть
    0.07
    �
    0.07
    ùy
    0.07
    ά
    0.07
    809
    0.06
     بار
    0.06
    usk
    0.06
     multipart
    0.06
    ACHINE
    0.06
    Act Density 0.052%

    No Known Activations