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

    Neuronpedia

    INDEX
    Explanations

    trabajos que hablan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aliados
    0.43
     Translator
    0.40
     Eins
    0.40
     investigadores
    0.38
     பக்தர்கள்
    0.38
     Bert
    0.38
     వీరి
    0.37
     Robo
    0.37
    之人
    0.37
     Erfol
    0.37
    POSITIVE LOGITS
    ştur
    0.42
    зня
    0.40
    ophor
    0.40
     servis
    0.40
    CLK
    0.39
     større
    0.38
    vyšší
    0.37
    мер
    0.37
     fale
    0.37
     repas
    0.36
    Act Density 0.000%

    No Known Activations