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

    Neuronpedia

    INDEX
    Explanations

    restriction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IfNeeded
    -0.07
    ‌باشد
    -0.07
     mention
    -0.06
     zp
    -0.06
     )}↵↵
    -0.06
    	Optional
    -0.06
     airing
    -0.06
    	meta
    -0.06
    ví
    -0.06
    57
    -0.06
    POSITIVE LOGITS
    _touch
    0.08
    (dot
    0.07
    Night
    0.07
    _statistics
    0.07
    -setup
    0.06
    untas
    0.06
    dex
    0.06
     ticking
    0.06
    .MODE
    0.06
     WELL
    0.06
    Act Density 0.006%

    No Known Activations