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

    Neuronpedia

    INDEX
    Explanations

    profile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     повлия
    0.37
    ব্ব
    0.37
    uradaki
    0.37
    besch
    0.36
     воспроиз
    0.36
    buscador
    0.36
     ಪ್ರಕಾರ
    0.35
    ложен
    0.35
    banding
    0.35
    новения
    0.34
    POSITIVE LOGITS
     profile
    0.80
    Profile
    0.77
     profiles
    0.72
     profiling
    0.71
     Profile
    0.70
     प्रोफाइल
    0.67
     профи
    0.66
     profil
    0.66
    Profil
    0.66
     Profil
    0.65
    Act Density 0.004%

    No Known Activations