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

    Neuronpedia

    INDEX
    Explanations

    CF

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CES
    -0.07
    /N
    -0.07
     Rental
    -0.07
    _photos
    -0.07
    ส
    -0.06
    annabin
    -0.06
    ardash
    -0.06
    /C
    -0.06
    ителем
    -0.06
    美
    -0.06
    POSITIVE LOGITS
    (if
    0.06
     plum
    0.06
     رئیس
    0.06
    icip
    0.06
     extensive
    0.06
    .*?)
    0.06
    .*
    0.06
    refixer
    0.06
    	final
    0.06
     appDelegate
    0.06
    Act Density 0.002%

    No Known Activations