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

    Neuronpedia

    INDEX
    Explanations

    place name prefixes and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RMSE
    0.63
      
    0.59
     checksum
    0.58
     chatbot
    0.57
     TypeScript
    0.56
     lowercase
    0.55
     IDE
    0.55
     instinct
    0.54
    s
    0.54
     silicon
    0.54
    POSITIVE LOGITS
    fecha
    0.75
    valment
    0.75
    extré
    0.74
    armée
    0.74
    huile
    0.73
    ujen
    0.72
    quantidade
    0.71
    chyné
    0.71
     jednej
    0.69
    hasil
    0.68
    Act Density 0.334%

    No Known Activations