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

    Neuronpedia

    INDEX
    Explanations

    postcode components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     downtown
    0.47
    owntown
    0.46
     mieście
    0.45
    वासियों
    0.45
     Scholarships
    0.44
     hometown
    0.44
    ulfate
    0.43
     lombok
    0.42
     Healthcare
    0.42
    맛집
    0.42
    POSITIVE LOGITS
    Dob
    0.46
     considere
    0.44
     Dob
    0.43
    考慮
    0.42
    Signal
    0.42
    Lik
    0.42
     어떤
    0.40
     sämt
    0.40
     gegevens
    0.39
     considerando
    0.39
    Act Density 0.001%

    No Known Activations