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

    Neuronpedia

    INDEX
    Explanations

    government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sweet
    -0.07
    _FREE
    -0.07
     time
    -0.07
     timeline
    -0.07
     Time
    -0.07
    _cookie
    -0.07
     wore
    -0.07
    related
    -0.07
    adden
    -0.07
    (dynamic
    -0.07
    POSITIVE LOGITS
     textStatus
    0.07
    agher
    0.06
    .Script
    0.06
     sharedPreferences
    0.06
    .credit
    0.06
     ση
    0.06
     Cathy
    0.06
    Fed
    0.06
    	sf
    0.06
    ql
    0.05
    Act Density 0.008%

    No Known Activations