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

    Neuronpedia

    INDEX
    Explanations

    hill station or repeats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chandeliers
    0.48
     boilers
    0.42
     fluctuations
    0.41
     Whitehead
    0.40
     chimneys
    0.39
     milestones
    0.39
     mites
    0.38
     rooftops
    0.38
     hiểu
    0.38
     हेल्पलाइन
    0.38
    POSITIVE LOGITS
    billy
    0.50
    ock
    0.50
    ides
    0.48
     overlooking
    0.46
    FIGURE
    0.44
     terrain
    0.43
    tops
    0.43
    lope
    0.43
    ็อก
    0.42
    IDES
    0.41
    Act Density 0.008%

    No Known Activations