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

    Neuronpedia

    INDEX
    Explanations

    customer service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    linalg
    1.05
    çe
    0.93
    zeitig
    0.91
     مقدس
    0.90
    á
    0.89
    amal
    0.86
    ou
    0.86
    äts
    0.86
    жен
    0.86
    ન્ટ
    0.84
    POSITIVE LOGITS
    isable
    1.76
     satisfaction
    1.51
    izability
    1.44
     Satisfaction
    1.44
    isation
    1.44
     tablo
    1.38
    ization
    1.33
    kring
    1.27
    riers
    1.25
    isations
    1.23
    Act Density 0.081%

    No Known Activations