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

    Neuronpedia

    INDEX
    Explanations

    code and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transgress
    0.65
     attendant
    0.63
    oxic
    0.63
     klin
    0.62
     Asht
    0.62
     algal
    0.62
     reinforced
    0.62
     ODBC
    0.62
     troop
    0.61
     pinpoint
    0.61
    POSITIVE LOGITS
        
    1.35
    1.00
       
    0.86
      
    0.80
         
    0.68
     सैकड़ों
    0.67
     Уда
    0.66
    <<<<
    0.65
    ılıyor
    0.65
    ésil
    0.64
    Act Density 0.415%

    No Known Activations