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

    Neuronpedia

    INDEX
    Explanations

    Head

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trás
    0.67
     estima
    0.66
    чої
    0.64
     estimations
    0.64
     Fairbanks
    0.64
     esboço
    0.64
    aughton
    0.63
     đến
    0.63
    핌
    0.62
    ociation
    0.62
    POSITIVE LOGITS
     head
    0.77
     lignes
    0.72
    rotechn
    0.70
    Head
    0.70
     Head
    0.70
    Lines
    0.70
    NL
    0.70
     watering
    0.67
    head
    0.66
    AD
    0.66
    Act Density 0.004%

    No Known Activations