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

    Neuronpedia

    INDEX
    Explanations

    building snowmen and sandcastles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bois
    0.46
     ადგილ
    0.43
     능력
    0.42
    的故事
    0.41
     עד
    0.40
    paralleled
    0.39
     аж
    0.39
     uridine
    0.38
    ันทร์
    0.38
    inien
    0.37
    POSITIVE LOGITS
     freezes
    0.52
     froze
    0.50
    fetch
    0.47
     freeze
    0.47
     Freeze
    0.47
     freezing
    0.45
     hielo
    0.45
    freeze
    0.44
     Seats
    0.44
     clasp
    0.42
    Act Density 0.006%

    No Known Activations