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

    Neuronpedia

    INDEX
    Explanations

    foreign and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    0.86
     offences
    0.83
     offence
    0.83
    fz
    0.80
     scepticism
    0.80
     छुटकारा
    0.80
     mlijeka
    0.78
     authorisation
    0.78
     persons
    0.77
     authorise
    0.76
    POSITIVE LOGITS
    รอง
    0.69
    
    0.66
     Immutable
    0.63
     পি
    0.63
     তাহলে
    0.62
     Deutsche
    0.62
    ೈನ
    0.61
     Scissors
    0.61
     Multin
    0.61
    いつも
    0.61
    Act Density 0.000%

    No Known Activations