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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pregnancy
    -0.07
    _membership
    -0.07
     hrá
    -0.07
    	no
    -0.07
     paternal
    -0.06
     Rating
    -0.06
    Booking
    -0.06
     parental
    -0.06
     emploi
    -0.06
     Specific
    -0.06
    POSITIVE LOGITS
    panic
    0.07
    FIELDS
    0.06
     unconditional
    0.06
    NECT
    0.06
    ّا
    0.06
     magnets
    0.06
     blí
    0.06
    endencies
    0.06
     navigationController
    0.06
    мі
    0.06
    Act Density 0.003%

    No Known Activations