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

    Neuronpedia

    INDEX
    Explanations

    travel itinerary details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mechanistic
    1.00
     cancerous
    0.99
     malignant
    0.98
     syntactic
    0.94
     electrodes
    0.92
     scalar
    0.92
     passivation
    0.91
     binary
    0.91
     plaintext
    0.89
     impurity
    0.87
    POSITIVE LOGITS
     sightseeing
    2.43
     itinerary
    2.30
     itineraries
    2.03
    観光
    1.95
     tourist
    1.92
     leisurely
    1.88
     Tourist
    1.84
     foodie
    1.82
     tourists
    1.79
     관광
    1.75
    Act Density 0.608%

    No Known Activations