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

    Neuronpedia

    INDEX
    Explanations

    judging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpol
    -0.08
    gelt
    -0.08
    einander
    -0.08
    list
    -0.08
     chants
    -0.08
     mee
    -0.07
     before
    -0.07
     kennt
    -0.07
    _GPU
    -0.07
     τί
    -0.07
    POSITIVE LOGITS
     ingesteld
    0.10
     tercih
    0.10
     voorkeur
    0.10
     предпочт
    0.09
     предпоч
    0.09
     Preference
    0.09
     доступа
    0.08
    endency
    0.08
     pilihan
    0.08
     accessed
    0.08
    Act Density 0.002%

    No Known Activations