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

    Neuronpedia

    INDEX
    Explanations

    Park followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    美味しい
    0.45
    ни
    0.44
     abundante
    0.41
    websocket
    0.41
    ેટ
    0.40
    ওয়ে
    0.39
    мато
    0.39
    тели
    0.39
    ում
    0.38
     Alhamdulillah
    0.38
    POSITIVE LOGITS
     parch
    0.43
    hill
    0.43
     pl
    0.42
     repos
    0.40
    plac
    0.40
     plaque
    0.40
     plats
    0.39
    park
    0.39
     lair
    0.39
     park
    0.38
    Act Density 0.001%

    No Known Activations