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

    Neuronpedia

    INDEX
    Explanations

    hiking trails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     summit
    0.89
     summits
    0.75
     zenith
    0.69
     climbers
    0.68
     entering
    0.67
     avalanche
    0.67
     hill
    0.66
     puncak
    0.66
     apex
    0.65
     slope
    0.65
    POSITIVE LOGITS
     trails
    1.96
     trail
    1.76
    trails
    1.68
    Trails
    1.62
     Trails
    1.59
    trail
    1.49
     Trail
    1.47
     TRAILS
    1.47
    Trail
    1.46
     paths
    1.40
    Act Density 0.378%

    No Known Activations