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

    Neuronpedia

    INDEX
    Explanations

    THC, F, complete, your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demandé
    1.15
     régional
    1.10
     privé
    1.01
     réserver
    0.91
    .
    0.90
     în
    0.88
     numéro
    0.88
     participé
    0.87
    _
    0.87
     putern
    0.86
    POSITIVE LOGITS
    បែប
    0.98
    দ্বিতীয়
    0.98
    менты
    0.96
     причины
    0.96
    ли
    0.95
    が多く
    0.95
    alities
    0.93
    お待ち
    0.93
    comings
    0.93
     defying
    0.92
    Act Density 0.001%

    No Known Activations